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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    луж
    -0.06
    _density
    -0.06
    Cab
    -0.06
    。“
    -0.06
    &W
    -0.06
    іг
    -0.06
    issance
    -0.06
     работ
    -0.06
    CID
    -0.06
     док
    -0.06
    POSITIVE LOGITS
    /rs
    0.07
     renewable
    0.06
    ")==
    0.06
    _rs
    0.06
     ποι
    0.06
    errar
    0.06
    _SHARE
    0.06
     psych
    0.06
    ิมพ
    0.06
     ext
    0.06
    Act Density 0.003%

    No Known Activations