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

    Neuronpedia

    INDEX
    Explanations

    .sup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    δη
    -0.06
     vyh
    -0.06
    crete
    -0.06
    body
    -0.06
     enjoying
    -0.06
    held
    -0.06
     愛
    -0.06
    Cool
    -0.06
    /J
    -0.06
    chází
    -0.06
    POSITIVE LOGITS
    .sup
    0.12
    .COMP
    0.08
     serializer
    0.08
     turnovers
    0.08
     Defender
    0.07
    。不过
    0.07
     contributor
    0.07
     mast
    0.07
     snapping
    0.07
     socialist
    0.07
    Act Density 0.002%

    No Known Activations