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

    Neuronpedia

    INDEX
    Explanations

    spreadsheets and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Communication
    -0.08
     FIXME
    -0.07
     Irish
    -0.07
    forcement
    -0.06
    Communication
    -0.06
    Australian
    -0.06
     Tablet
    -0.06
     Lock
    -0.06
     Australian
    -0.06
    (ts
    -0.06
    POSITIVE LOGITS
     FlatButton
    0.06
     LIMIT
    0.06
    dür
    0.06
    您的
    0.06
    .TRAILING
    0.06
     الكتاب
    0.06
     웹
    0.06
    าถ
    0.06
    .xrTableCell
    0.06
    ψ
    0.06
    Act Density 0.092%

    No Known Activations