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

    Neuronpedia

    INDEX
    Explanations

    year-over-year metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sekarang
    -1.49
     Jér
    -1.43
    edoria
    -1.41
    icestershire
    -1.41
     OGSÅ
    -1.40
     sabar
    -1.40
     …”
    -1.38
     mno
    -1.38
    тарь
    -1.38
     ?
    -1.35
    POSITIVE LOGITS
    '
    2.30
     the
    1.54
    —
    1.53
     общего
    1.45
    ta
    1.41
    ra
    1.34
    ed
    1.34
    er
    1.34
    ca
    1.33
    ire
    1.30
    Act Density 0.008%

    No Known Activations