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

    Neuronpedia

    INDEX
    Explanations

    electrons start or begin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    0.49
     বলছি
    0.48
    :=
    0.48
    ال
    0.46
    手
    0.45
    ي
    0.41
    FR
    0.40
    ه
    0.40
    ა
    0.40
    ميم
    0.40
    POSITIVE LOGITS
     animate
    0.46
     koc
    0.45
     Обще
    0.45
    supset
    0.43
     isotropy
    0.43
     congregate
    0.43
     boh
    0.42
     Nghi
    0.42
    hausen
    0.41
     epitope
    0.41
    Act Density 0.002%

    No Known Activations