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

    Neuronpedia

    INDEX
    Explanations

    um den Stein der

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కూ
    0.59
     Ñ
    0.57
     Rivals
    0.57
     Kün
    0.56
    ניים
    0.55
     Nested
    0.55
     Alley
    0.55
     Ters
    0.54
     Poc
    0.52
     Nil
    0.52
    POSITIVE LOGITS
     \
    0.59
    льних
    0.56
     demande
    0.55
    𝒈
    0.55
    е
    0.53
     имат
    0.52
    ๔
    0.52
     संग
    0.52
     وأ
    0.51
    jde
    0.50
    Act Density 0.001%

    No Known Activations