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

    Neuronpedia

    INDEX
    Explanations

    short timeframe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    பட
    0.41
    SystemFileSystem
    0.40
     License
    0.38
    CSharp
    0.38
    тор
    0.38
     теку
    0.38
     Хан
    0.37
    PathTemplate
    0.37
     হানি
    0.37
     concreta
    0.37
    POSITIVE LOGITS
    cellcolor
    0.43
     kana
    0.39
    iques
    0.39
     cheveux
    0.38
    neck
    0.37
    َّ
    0.37
    َّ
    0.36
     unaware
    0.36
     accusing
    0.36
     élèves
    0.35
    Act Density 0.000%

    No Known Activations