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

    Neuronpedia

    INDEX
    Explanations

    signed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /min
    -0.08
    =re
    -0.07
     생
    -0.07
    生物质
    -0.07
    (weight
    -0.07
    净
    -0.07
    毛泽东
    -0.06
    -alist
    -0.06
    CreateTime
    -0.06
    🆒
    -0.06
    POSITIVE LOGITS
    OURNAL
    0.08
     которые
    0.07
    .Matchers
    0.07
    document
    0.07
    מעניק
    0.07
    إجراءات
    0.07
    _PARAMS
    0.07
    PRINTF
    0.07
    기
    0.06
    TERM
    0.06
    Act Density 0.016%

    No Known Activations