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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )&&(
    -0.07
     AD
    -0.07
     rv
    -0.07
     üz
    -0.07
    �
    -0.07
    随之
    -0.07
    ｣
    -0.07
    haps
    -0.07
     постоя
    -0.07
    笙
    -0.07
    POSITIVE LOGITS
    weeks
    0.07
     flee
    0.07
     exceptional
    0.07
     Thần
    0.06
    <Float
    0.06
     societal
    0.06
     leveraging
    0.06
     gap
    0.06
     gauche
    0.06
    师傅
    0.06
    Act Density 0.019%

    No Known Activations