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

    Neuronpedia

    INDEX
    Explanations

    Code/math snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رش
    -0.06
     Shark
    -0.06
    Token
    -0.06
    <R
    -0.06
    ecz
    -0.06
    ulan
    -0.06
     Submission
    -0.06
     말
    -0.06
     модель
    -0.06
    리그
    -0.05
    POSITIVE LOGITS
    _ING
    0.07
    [len
    0.07
     dall
    0.07
    .tip
    0.06
    ink
    0.06
     teg
    0.06
    .userId
    0.06
    INK
    0.06
    tfoot
    0.06
     tú
    0.06
    Act Density 0.000%

    No Known Activations