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

    Neuronpedia

    INDEX
    Explanations

    authority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cunt
    -0.07
    _makeConstraints
    -0.07
    得
    -0.07
    מדה
    -0.06
    oha
    -0.06
    .YES
    -0.06
     teenagers
    -0.06
     suspense
    -0.06
    LEN
    -0.06
    줬
    -0.06
    POSITIVE LOGITS
     "__
    0.07
    [param
    0.07
    ('&
    0.07
    Song
    0.07
    (lines
    0.07
    毂
    0.06
    rna
    0.06
     shut
    0.06
     fungi
    0.06
     Treatment
    0.06
    Act Density 0.064%

    No Known Activations