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

    Neuronpedia

    INDEX
    Explanations

    Initial followed by next stage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    つける
    1.21
     humidifier
    1.13
    し
    1.12
    しっかり
    1.11
     raccol
    1.08
    性を
    1.06
     empie
    1.06
    чный
    1.05
    انی
    1.03
    気軽に
    1.03
    POSITIVE LOGITS
    0
    1.52
    4
    1.48
    3
    1.46
    b
    1.39
    ED
    1.35
    ب
    1.28
    6
    1.23
    it
    1.18
    5
    1.18
    م
    1.13
    Act Density 0.040%

    No Known Activations