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

    Neuronpedia

    INDEX
    Explanations

    significant and numerically significant terms in scientific or technical texts

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

    normally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISupport
    -0.59
     Infórmanos
    -0.58
     himo
    -0.55
    Tembelea
    -0.54
    Chham
    -0.53
    ſelf
    -0.52
     שוליים
    -0.51
     pinulongan
    -0.51
     Numerade
    -0.50
    Παραπομπές
    -0.50
    POSITIVE LOGITS
    kusen
    0.38
     claimed
    0.35
     szok
    0.33
     t
    0.32
     usually
    0.32
     ordinarily
    0.32
     often
    0.31
     mod
    0.31
     typically
    0.31
     normally
    0.31
    Act Density 0.084%

    No Known Activations