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

    Neuronpedia

    INDEX
    Explanations

    programming identifiers and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    賈
    0.26
    血管
    0.25
    峒
    0.24
     algodón
    0.23
     綿
    0.22
     communautés
    0.22
    ᠴ
    0.22
     、,
    0.22
    ⁽
    0.22
     diarrhoea
    0.22
    POSITIVE LOGITS
    if
    0.60
     if
    0.36
    continue
    0.32
    emit
    0.29
    setTimeout
    0.29
    this
    0.28
    while
    0.28
    fprintf
    0.28
    temp
    0.27
    switch
    0.27
    Act Density 0.130%

    No Known Activations