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

    Neuronpedia

    INDEX
    Explanations

    Descriptive imagery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.04
     Anſ
    -0.98
     myſelf
    -0.98
     photolibrary
    -0.96
     pleaſure
    -0.96
     Reſ
    -0.96
     purpoſe
    -0.94
     handwriting
    -0.94
     Eſ
    -0.92
     ſeveral
    -0.91
    POSITIVE LOGITS
    .
    0.73
    :
    0.58
    api
    0.54
    <b>
    0.52
     of
    0.52
    ,
    0.52
     on
    0.50
    ;
    0.50
     about
    0.49
     
    0.49
    Act Density 0.193%

    No Known Activations