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

    Neuronpedia

    INDEX
    Explanations

    articles and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Consum
    -0.07
    価格
    -0.07
    -0.07
     persists
    -0.07
    fonts
    -0.07
     cor
    -0.06
    numpy
    -0.06
    lero
    -0.06
     сказ
    -0.06
     choir
    -0.06
    POSITIVE LOGITS
    (XML
    0.06
     Args
    0.06
     uphold
    0.06
     TString
    0.06
    >{
    0.06
    ];
    0.06
    )*(
    0.06
    uli
    0.06
    _encoder
    0.06
    =n
    0.06
    Act Density 0.034%

    No Known Activations