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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ları
    -0.07
    licenses
    -0.07
     earthly
    -0.06
     возрасте
    -0.06
     redistribution
    -0.06
     Abbey
    -0.06
    levels
    -0.06
    ds
    -0.06
     vào
    -0.06
    hecy
    -0.06
    POSITIVE LOGITS
    MASK
    0.07
     فکر
    0.07
     TestData
    0.07
     mutation
    0.06
     Од
    0.06
     tartış
    0.06
     };
↵
    0.06
    ]]>
    0.06
     immunity
    0.06
    飞
    0.06
    Act Density 0.030%

    No Known Activations