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

    Neuronpedia

    INDEX
    Explanations

    career and education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elfare
    -0.07
    ń
    -0.07
    _RSP
    -0.07
    єв
    -0.06
    repr
    -0.06
     deferred
    -0.06
    ć
    -0.06
     chia
    -0.06
     bully
    -0.06
    icas
    -0.06
    POSITIVE LOGITS
     vua
    0.06
     Bà
    0.06
    も
    0.06
    ый
    0.06
     gắng
    0.06
    토토
    0.06
     Supplement
    0.06
    _SELF
    0.06
     explanation
    0.06
     paranormal
    0.06
    Act Density 0.123%

    No Known Activations