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

    Neuronpedia

    INDEX
    Explanations

    court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ❒
    -0.07
    fício
    -0.07
    福彩
    -0.07
     smugg
    -0.07
     חלק
    -0.07
    ủa
    -0.07
    ripsi
    -0.07
    alles
    -0.06
    Добав
    -0.06
     סוג
    -0.06
    POSITIVE LOGITS
     protagonist
    0.07
     MCP
    0.07
     extraordin
    0.07
    CACHE
    0.07
    WARDS
    0.07
    .ObjectMeta
    0.07
     prostituer
    0.06
    (INT
    0.06
    IL
    0.06
     Dates
    0.06
    Act Density 0.003%

    No Known Activations