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

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ologically
    -0.08
    �
    -0.07
     Paths
    -0.07
    Previous
    -0.07
    Wi
    -0.07
     öff
    -0.07
    Publication
    -0.07
     Ae
    -0.06
    xFFFF
    -0.06
     of
    -0.06
    POSITIVE LOGITS
    _SCHEMA
    0.07
     سيتم
    0.07
     survivors
    0.07
    Chrome
    0.07
    antages
    0.07
     형
    0.07
     cré
    0.07
    _custom
    0.07
     الأوروبي
    0.07
    STANCE
    0.07
    Act Density 0.007%

    No Known Activations