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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اطعة
    -0.07
    سطس
    -0.06
     E
    -0.06
    参照
    -0.06
     rewards
    -0.06
    SPACE
    -0.06
     voters
    -0.06
    embro
    -0.06
    ěstí
    -0.06
    _bounds
    -0.06
    POSITIVE LOGITS
     Accessed
    0.07
     trao
    0.07
    policy
    0.07
    Personally
    0.07
     hoch
    0.07
    ducted
    0.06
    (timestamp
    0.06
    cciones
    0.06
     disple
    0.06
     ：
    0.06
    Act Density 0.004%

    No Known Activations