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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cake
    -0.07
    кар
    -0.07
     yerleştir
    -0.06
    اساس
    -0.06
     пар
    -0.06
    pesan
    -0.06
    로운
    -0.06
    .subject
    -0.06
    ids
    -0.06
    estureRecognizer
    -0.06
    POSITIVE LOGITS
    _pot
    0.07
     Svět
    0.06
    ...↵↵
    0.06
    哥
    0.06
    ै।↵↵
    0.06
     classical
    0.06
     역사
    0.06
    (level
    0.05
    dü
    0.05
    '";↵
    0.05
    Act Density 0.009%

    No Known Activations