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

    Neuronpedia

    INDEX
    Explanations

    data parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     citroen
    -1.57
    躥
    -1.27
     inox
    -1.24
     rapporte
    -1.22
     Wants
    -1.21
    ՚
    -1.20
    त्र
    -1.20
     occuper
    -1.20
     knop
    -1.18
    ܸ
    -1.18
    POSITIVE LOGITS
     for
    1.84
     When
    1.61
     with
    1.45
    ;
    1.30
     and
    1.27
     kesempatan
    1.27
     That
    1.25
     should
    1.24
    When
    1.22
    1.20
    Act Density 0.020%

    No Known Activations