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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     학
    -0.07
     AVC
    -0.06
    HAS
    -0.06
     Rising
    -0.06
    ่าย
    -0.06
     Sting
    -0.06
    rb
    -0.06
    Bar
    -0.06
     policemen
    -0.06
     kı
    -0.06
    POSITIVE LOGITS
     Tomato
    0.07
    istributions
    0.07
    .telegram
    0.07
    -auth
    0.06
    ErrorException
    0.06
    ์ช
    0.06
    asyon
    0.06
    .handler
    0.06
     sentenced
    0.06
     callBack
    0.06
    Act Density 0.008%

    No Known Activations