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

    Neuronpedia

    INDEX
    Explanations

    plum

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fwrite
    -0.06
    leriyle
    -0.06
    ंगठन
    -0.06
    Ngày
    -0.06
     FedEx
    -0.06
     ¥
    -0.06
    agini
    -0.06
    กฎ
    -0.05
     PASS
    -0.05
    Rights
    -0.05
    POSITIVE LOGITS
    驾
    0.07
    -builder
    0.07
     같습니다
    0.07
     SEXP
    0.07
     up
    0.07
    خص
    0.07
    군요
    0.06
    epam
    0.06
     entirely
    0.06
    .todos
    0.06
    Act Density 0.001%

    No Known Activations