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

    Neuronpedia

    INDEX
    Explanations

    specific model, species, or date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oğ
    0.43
    Chia
    0.42
    ANDO
    0.42
    骢
    0.41
     మరియు
    0.40
     Фа
    0.40
    竇
    0.39
    RawContext
    0.39
     Наде
    0.38
     вя
    0.38
    POSITIVE LOGITS
     جل
    0.41
     preceded
    0.41
    ข
    0.39
     lengthy
    0.37
    global
    0.36
    }\
    0.35
    وبة
    0.35
     לת
    0.35
     জটিল
    0.34
     komplex
    0.34
    Act Density 0.000%

    No Known Activations