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

    Neuronpedia

    INDEX
    Explanations

    Who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    47
    -0.07
    108
    -0.07
    WithOptions
    -0.06
     Clay
    -0.06
    ja
    -0.06
     Security
    -0.06
    .setCellValue
    -0.06
     tình
    -0.06
    威
    -0.06
     Мак
    -0.06
    POSITIVE LOGITS
    emi
    0.08
    ーパー
    0.06
     Bennett
    0.06
     результат
    0.06
     організації
    0.06
     مکانی
    0.06
     نه
    0.06
     Alic
    0.06
     polish
    0.06
    보험
    0.06
    Act Density 0.013%

    No Known Activations