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

    Neuronpedia

    INDEX
    Explanations

    Times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jis
    -0.08
    fuck
    -0.08
    突
    -0.08
    ++)
    -0.07
    Kel
    -0.07
    -linux
    -0.07
    facet
    -0.07
    /chat
    -0.07
    five
    -0.07
    扑
    -0.07
    POSITIVE LOGITS
     الكثير
    0.07
    🏞
    0.07
     Certainly
    0.07
    了一批
    0.07
    涉案
    0.06
    \helpers
    0.06
    大幅提升
    0.06
    뿐만
    0.06
     [*
    0.06
    ＝
    0.06
    Act Density 0.003%

    No Known Activations