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

    Neuronpedia

    INDEX
    Explanations

    Mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NUMBER
    -0.07
     etwas
    -0.07
    柄
    -0.07
    -circle
    -0.07
    ชาย
    -0.07
    Specify
    -0.07
    _sess
    -0.06
    orgeous
    -0.06
    dbName
    -0.06
     Husband
    -0.06
    POSITIVE LOGITS
     Enforcement
    0.08
    amo
    0.07
     Львів
    0.06
     unlaw
    0.06
    viron
    0.06
     enforcement
    0.06
    pol
    0.06
     Дж
    0.06
     ----------------------------------------------------------------------------------------------------------------
    0.06
    throws
    0.06
    Act Density 0.036%

    No Known Activations