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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     binge
    -0.07
     XOR
    -0.07
     arrogant
    -0.06
     laughter
    -0.06
     katkı
    -0.06
    _TH
    -0.06
    aub
    -0.06
    フィ
    -0.06
     submarine
    -0.06
    _define
    -0.06
    POSITIVE LOGITS
     coppia
    0.07
    .AutoScale
    0.06
    .filePath
    0.06
    /url
    0.06
    -side
    0.06
     EPS
    0.06
    .getResources
    0.06
    mon
    0.06
     di
    0.06
    FFFF
    0.06
    Act Density 0.006%

    No Known Activations