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

    Neuronpedia

    INDEX
    Explanations

    Percentages and periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    のだ
    -0.06
     해결
    -0.06
     обяз
    -0.06
    aceutical
    -0.06
    Ы
    -0.06
    -fetch
    -0.06
    줄
    -0.06
     매매
    -0.06
    凉
    -0.06
    だけ
    -0.06
    POSITIVE LOGITS
    ความค
    0.07
     Southern
    0.07
    incible
    0.06
     αδ
    0.06
     Threads
    0.06
     tph
    0.06
    bagai
    0.06
    .INSTANCE
    0.06
    Aff
    0.06
    Triangle
    0.06
    Act Density 0.008%

    No Known Activations