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

    Neuronpedia

    INDEX
    Explanations

    diaphragms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ็ก
    -0.07
     tren
    -0.07
     Severity
    -0.06
    字段
    -0.06
    (loss
    -0.06
    f
    -0.06
    _actor
    -0.06
    ف
    -0.06
     licking
    -0.06
    ett
    -0.06
    POSITIVE LOGITS
    aphrag
    0.14
     bridge
    0.07
    mah
    0.07
     بغ
    0.07
    Moh
    0.07
    -par
    0.07
    spir
    0.06
     всей
    0.06
     dominate
    0.06
    ।↵↵
    0.06
    Act Density 0.000%

    No Known Activations