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

    Neuronpedia

    INDEX
    Explanations

    words related to choosing, whether by decision or randomness

    oai_token-act-pair · gemini-2.0-flash

    which when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.68
     مشين
    -0.66
    oredCriteria
    -0.63
     Roskov
    -0.61
    twimg
    -0.61
    _));
    -0.59
    createComponent
    -0.58
    PINES
    -0.57
    artiges
    -0.56
    Geplaatst
    -0.54
    POSITIVE LOGITS
     how
    1.05
     what
    0.86
     Monfieur
    0.83
    what
    0.81
     ſtate
    0.79
    how
    0.77
     HOW
    0.77
     Chriftian
    0.76
     Reſ
    0.75
     Theſe
    0.75
    Act Density 2.960%

    No Known Activations