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

    Neuronpedia

    INDEX
    Explanations

    import statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    І
    1.46
    larından
    1.45
    litre
    1.43
    lerinden
    1.38
     yanı
    1.38
    laid
    1.33
    CONTAIN
    1.31
    সমূ
    1.27
    doesn
    1.27
    lined
    1.26
    POSITIVE LOGITS
    '
    1.80
    ان
    1.77
    了两
    1.76
    ри
    1.55
    ars
    1.55
    ir
    1.51
    $
    1.49
    ം
    1.48
    em
    1.46
    ни
    1.45
    Act Density 0.718%

    No Known Activations