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

    Neuronpedia

    INDEX
    Explanations

    e asi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hens
    0.41
     Chico
    0.40
     elegan
    0.40
    Lower
    0.39
     Vek
    0.38
     pencils
    0.38
    каў
    0.38
     enthr
    0.38
    뵌
    0.38
     Chap
    0.37
    POSITIVE LOGITS
    asi
    0.53
    asy
    0.52
    ásico
    0.50
    ası
    0.49
    asio
    0.45
    assel
    0.44
    ASY
    0.44
    ασ
    0.44
    asih
    0.43
    aster
    0.43
    Act Density 0.003%

    No Known Activations