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

    Neuronpedia

    INDEX
    Explanations

    Find, Comparative, abstraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ethnic
    0.45
    ̣
    0.45
    ˛
    0.44
    を持
    0.43
    enl
    0.42
    證明
    0.42
    ジナル
    0.42
    getMetering
    0.42
     ži
    0.41
    Ꭲ
    0.41
    POSITIVE LOGITS
    ાલ
    0.50
    ب
    0.49
    ாளர்க
    0.48
    اند
    0.47
    ाइन
    0.46
    itat
    0.46
     creen
    0.44
    ించడానికి
    0.44
    ف
    0.44
     first
    0.44
    Act Density 0.001%

    No Known Activations