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

    Neuronpedia

    INDEX
    Explanations

    Non-natural language text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ة
    -0.07
     Tournament
    -0.07
    ерш
    -0.06
    _backup
    -0.06
     аг
    -0.06
    FOR
    -0.06
    sku
    -0.06
    Β
    -0.06
    Aux
    -0.06
    Fuse
    -0.06
    POSITIVE LOGITS
     तब
    0.07
     deposits
    0.07
     Protest
    0.06
    هدف
    0.06
     methane
    0.06
    (window
    0.06
    uart
    0.06
     prank
    0.06
     پرداز
    0.06
    omid
    0.06
    Act Density 0.034%

    No Known Activations