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

    Neuronpedia

    INDEX
    Explanations

    information context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ům
    0.46
    lerinin
    0.45
    Breakpoint
    0.43
    ется
    0.43
    ără
    0.42
    LongNumber
    0.42
    ewhat
    0.42
    levation
    0.41
    겉
    0.41
    ี่ย
    0.41
    POSITIVE LOGITS
     to
    0.68
     for
    0.67
     from
    0.63
     in
    0.63
     on
    0.61
     and
    0.61
     is
    0.57
     of
    0.54
     with
    0.51
     such
    0.50
    Act Density 0.064%

    No Known Activations