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

    Neuronpedia

    INDEX
    Explanations

    words indicating positive sentiment or quality

    oai_token-act-pair · gemini-2.0-flash

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     looking
    -0.65
     looked
    -0.63
     look
    -0.61
    looking
    -0.60
    Looking
    -0.60
     Looking
    -0.59
     Looked
    -0.57
    look
    -0.56
    looked
    -0.56
    LOOKING
    -0.54
    POSITIVE LOGITS
     незавершена
    0.83
     <<<<<<<<<<<<<<
    0.69
    Hozzáférés
    0.68
    PYX
    0.67
    PropertyChanging
    0.66
     Roskov
    0.64
     invokingState
    0.63
    andaş
    0.63
    ftagPool
    0.63
     onAnimation
    0.62
    Act Density 12.242%

    No Known Activations