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

    Neuronpedia

    INDEX
    Explanations

    Math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Leap
    -0.08
     virus
    -0.08
     exam
    -0.07
    -0.07
     whenever
    -0.07
     Leap
    -0.07
    Bor
    -0.07
    考试
    -0.07
     graduate
    -0.07
    (es
    -0.06
    POSITIVE LOGITS
     પોતાની
    0.09
    cemic
    0.09
    ոտ
    0.09
    ご了承ください
    0.09
     لقاء
    0.08
     સમયે
    0.08
    ાર
    0.08
    vodu
    0.08
    .cor
    0.08
    ombra
    0.08
    Act Density 0.023%
    No Known Activations