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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Notably
    1.43
     எனும்
    1.43
     Серге
    1.37
     என
    1.37
    嶌
    1.36
     Đặc
    1.35
    醿
    1.35
     Notably
    1.33
    lexeme
    1.33
     textAlign
    1.32
    POSITIVE LOGITS
     espada
    0.98
     Pant
    0.98
     espiritual
    0.93
     Yud
    0.91
     B
    0.90
     Edo
    0.87
     Male
    0.87
     pantry
    0.86
     costumbres
    0.86
     hambre
    0.85
    Act Density 0.004%

    No Known Activations