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

    Neuronpedia

    INDEX
    Explanations

    Zero, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -0.84
    ">:
    -0.81
    \{\\
    -0.79
    findpost
    -0.76
     Himo
    -0.76
    "]);
    -0.71
     estekak
    -0.70
     odkazy
    -0.69
     fieldNum
    -0.69
     وتسجيلات
    -0.68
    POSITIVE LOGITS
     (
    0.51
    ,
    0.43
     of
    0.43
     world
    0.41
     re
    0.41
     to
    0.40
     for
    0.40
     situation
    0.40
     quant
    0.39
     regarding
    0.39
    Act Density 0.003%

    No Known Activations