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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .djangoproject
    -0.07
     wholesome
    -0.07
    ="_
    -0.07
     Ded
    -0.07
    endoza
    -0.06
    erif
    -0.06
    価格
    -0.06
     req
    -0.06
    /tr
    -0.06
     صف
    -0.06
    POSITIVE LOGITS
    تان
    0.07
    (point
    0.07
    (theme
    0.06
    .Generic
    0.06
    ри
    0.06
    .Relative
    0.06
    0.06
    =[
    0.06
    .Anchor
    0.06
     Φ
    0.06
    Act Density 0.073%

    No Known Activations