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

    Neuronpedia

    INDEX
    Explanations

    phone lines and service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нің
    0.64
     말미암아
    0.56
     FutureWarning
    0.55
    рия
    0.54
     институт
    0.54
     것은
    0.54
     каким
    0.54
    èrent
    0.53
     unlaw
    0.52
     vật
    0.52
    POSITIVE LOGITS
     for
    0.78
    ن
    0.77
    उ
    0.72
    ↵↵
    0.69
    न
    0.65
     and
    0.65
    Session
    0.64
    n
    0.61
    م
    0.61
    Da
    0.60
    Act Density 0.002%

    No Known Activations