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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    档
    -0.07
    dera
    -0.07
    .docs
    -0.06
    nda
    -0.06
     sung
    -0.06
    YA
    -0.06
    _em
    -0.06
    ston
    -0.06
    actual
    -0.06
    ţ
    -0.06
    POSITIVE LOGITS
     trade
    0.08
    诡
    0.07
     وزارة
    0.07
    탁
    0.07
    uesday
    0.07
    Ⱄ
    0.07
     quà
    0.07
    משא
    0.07
    exterity
    0.07
    holds
    0.07
    Act Density 0.196%

    No Known Activations