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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jaguar
    -0.08
     lights
    -0.07
    ">';↵
    -0.06
    rokes
    -0.06
    $username
    -0.06
     Kidd
    -0.06
     콜
    -0.06
    fu
    -0.06
    Fill
    -0.06
    23
    -0.06
    POSITIVE LOGITS
    _skills
    0.07
    <Character
    0.06
     zprav
    0.06
    -components
    0.06
     комплекс
    0.06
     wła
    0.06
     principalmente
    0.06
     awhile
    0.06
    ../
    0.06
    (para
    0.06
    Act Density 0.393%

    No Known Activations