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

    Neuronpedia

    INDEX
    Explanations

    admit or deny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nam
    -0.07
    amet
    -0.07
    ularity
    -0.07
     highs
    -0.07
    ์น
    -0.06
    爸
    -0.06
    ULAR
    -0.06
     από
    -0.06
    摘要
    -0.06
    萬
    -0.06
    POSITIVE LOGITS
    .Dict
    0.07
    Decl
    0.07
    _extensions
    0.06
    سان
    0.06
     гра
    0.06
    _PARSE
    0.06
    を行
    0.06
    ظٹط
    0.06
     referring
    0.06
    .Contracts
    0.06
    Act Density 0.095%

    No Known Activations