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

    Neuronpedia

    INDEX
    Explanations

    emma links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     پنجاب
    0.39
    ಪಿ
    0.39
    EnableCOMDAT
    0.37
     અમે
    0.36
    壹百
    0.36
    TRS
    0.36
     جوان
    0.36
    GM
    0.35
    uja
    0.35
    Су
    0.35
    POSITIVE LOGITS
    ホームページ
    0.46
     شيء
    0.41
     disponibilidad
    0.40
     पोर्टल
    0.40
     disponibilité
    0.40
     introductory
    0.39
     preview
    0.39
     invite
    0.39
     webpage
    0.39
    概
    0.39
    Act Density 0.006%

    No Known Activations