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

    Neuronpedia

    INDEX
    Explanations

    programming discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ан
    -0.06
    ת
    -0.06
     ele
    -0.06
    )|
    -0.06
    )+'
    -0.06
     leaking
    -0.06
    mj
    -0.06
     Mull
    -0.06
    ‌رس
    -0.06
    ΕΧ
    -0.06
    POSITIVE LOGITS
     Soviets
    0.08
    زو
    0.07
     Camden
    0.07
    вей
    0.06
    hoot
    0.06
    Nova
    0.06
     Gallup
    0.06
    quence
    0.06
    werp
    0.06
    (dialog
    0.06
    Act Density 0.064%

    No Known Activations