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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Summers
    -0.07
     Swinger
    -0.06
    /downloads
    -0.06
     QColor
    -0.06
    rale
    -0.06
     posto
    -0.06
    TextInput
    -0.06
     Мак
    -0.06
    _feats
    -0.06
     القانون
    -0.06
    POSITIVE LOGITS
    228
    0.07
    29
    0.07
    ์บ
    0.06
    ICY
    0.06
    τι
    0.06
     misleading
    0.06
     친
    0.06
     point
    0.06
    AAD
    0.06
     lie
    0.06
    Act Density 0.000%

    No Known Activations