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

    Neuronpedia

    INDEX
    Explanations

    references to women and character roles in media

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

    actor sequel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     goud
    -0.41
     preocupes
    -0.39
    awtextra
    -0.38
    Sloth
    -0.36
     pade
    -0.33
    WindowConstants
    -0.33
     mesin
    -0.32
     franqu
    -0.31
     huid
    -0.31
    current
    -0.31
    POSITIVE LOGITS
    Personendaten
    0.60
    RenderAtEndOf
    0.59
    +#+
    0.54
    évaluateur
    0.50
    AnimationsModule
    0.48
     invokingState
    0.47
    zeptember
    0.46
    psies
    0.46
    elemField
    0.46
    Autoritní
    0.45
    Act Density 0.040%

    No Known Activations