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

    Neuronpedia

    INDEX
    Explanations

    All-in-one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    final
    -0.07
    istra
    -0.07
    Yesterday
    -0.07
    Longitude
    -0.07
     conc
    -0.07
    握手
    -0.06
     shred
    -0.06
     FD
    -0.06
     losses
    -0.06
     FAMILY
    -0.06
    POSITIVE LOGITS
    قدرة
    0.07
    لال
    0.07
    uação
    0.07
    pass
    0.07
    kazał
    0.07
    AL
    0.07
    .NewLine
    0.07
    ул
    0.07
    _PROPERTIES
    0.06
     الك
    0.06
    Act Density 0.006%

    No Known Activations