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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    individual
    -0.09
    elastic
    -0.07
    (BitConverter
    -0.07
    dismiss
    -0.06
    лению
    -0.06
    hrs
    -0.06
    _occ
    -0.06
     rings
    -0.06
     تو
    -0.06
    canonical
    -0.06
    POSITIVE LOGITS
     Devlet
    0.08
     PageSize
    0.06
     đỏ
    0.06
     TSRMLS
    0.06
    oài
    0.06
    ...,
    0.06
    छ
    0.06
    ="(
    0.06
     []↵↵
    0.06
     Faculty
    0.06
    Act Density 0.077%

    No Known Activations