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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     předpok
    -0.07
     evasion
    -0.06
     Fal
    -0.06
     east
    -0.06
     sắt
    -0.06
     μετα
    -0.06
     geographical
    -0.06
    항
    -0.05
     mutex
    -0.05
     gió
    -0.05
    POSITIVE LOGITS
    _header
    0.07
     moderator
    0.07
     Prostit
    0.06
    бер
    0.06
    .Calendar
    0.06
     dad
    0.06
     scans
    0.06
    /Delete
    0.06
    (connect
    0.06
    ienne
    0.06
    Act Density 0.000%

    No Known Activations