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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    、高
    -0.07
     Responsibilities
    -0.07
     lows
    -0.07
    ADO
    -0.06
    ado
    -0.06
    (H
    -0.06
     swath
    -0.06
     свою
    -0.06
    -parse
    -0.06
    POSITIVE LOGITS
     rest
    0.06
    (fabs
    0.06
    ные
    0.06
     Tel
    0.06
     immune
    0.06
     아니라
    0.06
    ...";↵
    0.06
    иты
    0.06
     Reference
    0.06
    referrer
    0.06
    Act Density 0.005%

    No Known Activations