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

    Neuronpedia

    INDEX
    Explanations

    tos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    汽车
    -0.07
     Mastery
    -0.06
    طاق
    -0.06
    Ele
    -0.06
    اص
    -0.06
    ické
    -0.06
    $class
    -0.06
     jemand
    -0.06
    Fatal
    -0.06
    }],
    -0.06
    POSITIVE LOGITS
    tos
    0.20
    دا
    0.07
     Denis
    0.06
     ForCanBeConvertedToForeach
    0.06
    ॉफ
    0.06
    TO
    0.06
    attached
    0.06
     Vác
    0.06
    .source
    0.06
    .Light
    0.06
    Act Density 0.002%

    No Known Activations