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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >We
    -0.06
    _ud
    -0.06
    ominated
    -0.06
    _PAGE
    -0.06
    "For
    -0.06
     Astro
    -0.06
     Dawson
    -0.06
     Dre
    -0.06
    .Do
    -0.06
     Kont
    -0.06
    POSITIVE LOGITS
     asıl
    0.07
    rar
    0.07
    有
    0.06
    his
    0.06
    気
    0.06
     следующ
    0.06
     điện
    0.06
     quieter
    0.06
     द
    0.06
     freshman
    0.06
    Act Density 0.006%

    No Known Activations