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

    Neuronpedia

    INDEX
    Explanations

    watermarking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bitte
    -0.07
    yaml
    -0.06
    $where
    -0.06
     också
    -0.06
    TypeDef
    -0.06
     $("#"
    -0.06
    吾
    -0.06
    /book
    -0.06
    (cli
    -0.06
    _LL
    -0.06
    POSITIVE LOGITS
    -prev
    0.07
     INFORMATION
    0.06
     celebration
    0.06
     sanctions
    0.06
     tuyên
    0.06
    pellier
    0.06
    fv
    0.06
    _primitive
    0.06
     transmitted
    0.06
     relationships
    0.06
    Act Density 0.009%

    No Known Activations