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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts

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

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -0.62
     dezelve
    -0.59
    Filmografia
    -0.57
     numberWith
    -0.57
     pembun
    -0.53
    genodigd
    -0.53
     mijne
    -0.52
    limiento
    -0.52
     miniaturka
    -0.52
    ualaikum
    -0.51
    POSITIVE LOGITS
     surreal
    0.43
     style
    0.42
     atmosphere
    0.40
     ap
    0.37
     rocky
    0.37
     mim
    0.36
     circular
    0.36
     ambience
    0.36
    дак
    0.35
     mode
    0.35
    Act Density 0.022%

    No Known Activations