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
    _overlap
    -0.07
     Scientists
    -0.06
     latitude
    -0.06
    lers
    -0.06
    (pos
    -0.06
    urons
    -0.06
     parish
    -0.06
     superst
    -0.06
     convers
    -0.06
     humano
    -0.06
    POSITIVE LOGITS
    存
    0.07
    감
    0.07
    督
    0.07
     rendered
    0.06
    估
    0.06
     EOF
    0.06
    جميع
    0.06
    kın
    0.06
    онд
    0.06
     잘
    0.06
    Act Density 0.000%

    No Known Activations