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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pracov
    -0.06
    Ế
    -0.06
     以
    -0.06
     Roe
    -0.06
    ूँ
    -0.06
    Про
    -0.06
    _proba
    -0.06
    위원
    -0.06
     مان
    -0.06
    犯罪
    -0.06
    POSITIVE LOGITS
    .Query
    0.07
    olest
    0.06
    eptal
    0.06
    (QL
    0.06
    (segment
    0.06
    otta
    0.06
    fed
    0.06
     compan
    0.06
     THR
    0.06
    ์
    0.06
    Act Density 0.003%

    No Known Activations