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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     software
    -0.07
     guar
    -0.07
    _metadata
    -0.07
     ordering
    -0.07
    endment
    -0.07
    -${
    -0.06
    _peak
    -0.06
     strives
    -0.06
     research
    -0.06
     Origins
    -0.06
    POSITIVE LOGITS
     آلة
    0.06
     확실
    0.06
     월세
    0.06
     Pais
    0.06
     سلامت
    0.06
    (GL
    0.06
    DEV
    0.05
     QSize
    0.05
     disables
    0.05
    @PostMapping
    0.05
    Act Density 0.009%

    No Known Activations