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

    Neuronpedia

    INDEX
    Explanations

    multi-language commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     longitudinale
    0.47
     формирование
    0.47
    MiddleLine
    0.47
    newMark
    0.47
    tcpHeader
    0.46
     प्रश
    0.46
    skraft
    0.46
    ડા
    0.46
     דר
    0.46
    Unifier
    0.46
    POSITIVE LOGITS
     by
    0.71
     to
    0.67
     your
    0.64
     you
    0.59
     tele
    0.57
     his
    0.55
     well
    0.54
     one
    0.53
     my
    0.51
     file
    0.50
    Act Density 0.000%

    No Known Activations