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

    Neuronpedia

    INDEX
    Explanations

    historical context narratives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ang
    0.42
    jska
    0.42
    ঞ্জেল
    0.41
    APs
    0.40
    僵
    0.40
    进行
    0.40
    ova
    0.39
     poprzez
    0.38
    ologa
    0.38
    惊
    0.38
    POSITIVE LOGITS
     Faculty
    0.42
    _="
    0.41
     faculté
    0.41
    sendKeyDown
    0.40
     Spirituality
    0.40
    жён
    0.39
     resentment
    0.39
     Sends
    0.39
    枨
    0.38
     まま
    0.38
    Act Density 0.001%

    No Known Activations