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

    Neuronpedia

    INDEX
    Explanations

    specific topics or areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.48
     খাঁ
    0.44
     are
    0.40
    mol
    0.39
     and
    0.39
    ner
    0.39
     che
    0.39
     compulsive
    0.38
    go
    0.38
    water
    0.38
    POSITIVE LOGITS
    ⚙
    0.42
    \{\
    0.40
    केज
    0.40
    过于
    0.40
    лянчук
    0.39
    板块
    0.38
    玾
    0.38
    条例
    0.38
     Отече
    0.38
    ﻼ
    0.38
    Act Density 0.000%

    No Known Activations