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

    Neuronpedia

    INDEX
    Explanations

    Original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Regional
    -0.07
     collectively
    -0.07
     Categories
    -0.06
    .Mapping
    -0.06
    erie
    -0.06
    分解
    -0.06
     amateur
    -0.06
     الإدارة
    -0.06
     distributing
    -0.06
     village
    -0.06
    POSITIVE LOGITS
    /******/↵
    0.08
     subj
    0.07
    藉
    0.07
    意見
    0.06
     repro
    0.06
    核电
    0.06
    ())↵
    0.06
     سور
    0.06
    渑
    0.06
    лот
    0.06
    Act Density 0.004%

    No Known Activations