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

    Neuronpedia

    INDEX
    Explanations

    words related to economics and numerical data related to people and money.

    oai_token-act-pair · gemini-2.0-flash

    Punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theſe
    -1.02
     Anſ
    -0.91
     Diſ
    -0.90
     Reſ
    -0.86
     Houſe
    -0.83
     faſt
    -0.81
     purpoſe
    -0.79
     themſelves
    -0.78
     becauſe
    -0.77
     houſe
    -0.77
    POSITIVE LOGITS
    ,
    0.61
     -
    0.54
     –
    0.52
    .
    0.48
     —
    0.45
    ;
    0.44
    !
    0.43
    ParallelGroup
    0.43
     −
    0.41
     represent
    0.40
    Act Density 6.510%

    No Known Activations