Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of fascination and complex emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    acknowledgment, denial, or property

    np_acts-logits-general · gemini-2.5-flash-lite

    words expressing strong subjective opinion or emotion (highly evaluative or emotive language).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.57
     ویکی‌پدی
    -0.55
     Instability
    -0.48
     ujednoznacz
    -0.47
    GOTREF
    -0.45
    AndEndTag
    -0.44
     intptr
    -0.43
     Truth
    -0.43
    lihood
    -0.43
     Jefus
    -0.42
    POSITIVE LOGITS
    RRect
    0.40
     soñar
    0.38
     mariposas
    0.36
     Vordergrund
    0.36
     araña
    0.35
     hambre
    0.35
     juzg
    0.34
     defaultstate
    0.33
     piedras
    0.33
     corazones
    0.33
    Act Density 0.527%

    No Known Activations