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

    Neuronpedia

    INDEX
    Explanations

    locations and proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $body
    -0.06
    립니다
    -0.06
     Lesbian
    -0.06
    .Delete
    -0.06
     Routine
    -0.06
     význam
    -0.06
    ["$
    -0.06
     شي
    -0.06
     undes
    -0.06
    Keyword
    -0.06
    POSITIVE LOGITS
    ‌آ
    0.07
     indo
    0.07
    èle
    0.06
     dashed
    0.06
    _countries
    0.06
     prizes
    0.06
     RCMP
    0.06
    emas
    0.06
    -E
    0.06
    smouth
    0.06
    Act Density 0.138%

    No Known Activations