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

    Neuronpedia

    INDEX
    Explanations

    relationships and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acariy
    0.33
     సమస్య
    0.31
     יכול
    0.30
     വിവിധ
    0.30
     decenas
    0.30
    pieceSelection
    0.29
     pediat
    0.29
     FUNDS
    0.29
     fonctionner
    0.29
     metodologia
    0.29
    POSITIVE LOGITS
     itself
    0.36
    it
    0.34
     the
    0.34
     its
    0.33
     to
    0.32
     it
    0.32
     that
    0.32
     you
    0.31
    l
    0.30
    ↵
    0.30
    Act Density 0.266%

    No Known Activations