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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ogy
    -0.07
    历
    -0.06
     categorical
    -0.06
    歷
    -0.06
     Generic
    -0.06
     eldest
    -0.06
    當
    -0.06
    plus
    -0.06
    Scan
    -0.06
     конт
    -0.06
    POSITIVE LOGITS
    moduleName
    0.07
    ratings
    0.06
    σμα
    0.06
     Compatibility
    0.06
    (reordered
    0.06
     مطلب
    0.06
     cumbersome
    0.06
     masking
    0.06
    Meanwhile
    0.06
    (low
    0.06
    Act Density 0.029%

    No Known Activations