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

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Audit
    -0.07
    emergency
    -0.07
     hotter
    -0.07
    bias
    -0.07
    ätz
    -0.07
     serviços
    -0.06
     framework
    -0.06
    red
    -0.06
    “To
    -0.06
    ’re
    -0.06
    POSITIVE LOGITS
     мощ
    0.07
     popcorn
    0.06
    ＼＼
    0.06
     Janeiro
    0.06
     перш
    0.06
     останов
    0.06
    UN
    0.06
    (items
    0.06
     ول
    0.06
     Luk
    0.06
    Act Density 0.030%

    No Known Activations