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

    Neuronpedia

    INDEX
    Explanations

    gesturing, clutching, burying, dropping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    2.00
    ي
    1.85
    ا
    1.43
    ما
    1.40
     valamint
    1.32
     avances
    1.30
    写法
    1.30
     Replace
    1.28
    ご連絡
    1.27
    י
    1.27
    POSITIVE LOGITS
    ной
    1.19
    d
    1.18
    ер
    1.16
    ೀನ
    1.13
    ocyan
    1.12
    tahun
    1.12
    苣
    1.12
    Categorie
    1.11
    tel
    1.10
    ルス
    1.09
    Act Density 0.028%

    No Known Activations