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

    Neuronpedia

    INDEX
    Explanations

    included notes or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zoho
    0.49
    (-
    0.46
    ዷ
    0.45
     tâ
    0.45
     Yangzhou
    0.45
     Nunes
    0.43
     CaCO
    0.43
     Soh
    0.42
    余
    0.42
     Bhajan
    0.41
    POSITIVE LOGITS
     گراف
    0.49
     تجهیز
    0.47
    altung
    0.46
     شناخت
    0.46
     espionage
    0.46
     گروه
    0.46
    RAFT
    0.45
     څرنګوالی
    0.45
     குழ
    0.45
    借鉴
    0.45
    Act Density 0.004%

    No Known Activations