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

    Neuronpedia

    INDEX
    Explanations

    cout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dep
    -0.06
     astonishing
    -0.06
    _Str
    -0.06
     Time
    -0.06
    ultural
    -0.06
    retty
    -0.06
    .Write
    -0.06
     图
    -0.06
     Sacred
    -0.06
    wild
    -0.06
    POSITIVE LOGITS
    xFD
    0.06
     MVP
    0.06
     зв
    0.06
    μη
    0.06
    قات
    0.06
    150
    0.06
     finanční
    0.06
     founders
    0.06
    ellery
    0.06
    ilm
    0.06
    Act Density 0.001%

    No Known Activations