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

    Neuronpedia

    INDEX
    Explanations

    title preceding a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     where
    -2.70
     and
    -2.45
     in
    -2.39
     until
    -2.00
    してました
    -1.98
     within
    -1.98
     could
    -1.95
     who
    -1.95
     this
    -1.88
     these
    -1.84
    POSITIVE LOGITS
     of
    2.41
     '
    1.96
    carus
    1.84
    OOOO
    1.78
     "'
    1.77
     tillegg
    1.72
     récemment
    1.68
     gouttes
    1.67
     óra
    1.66
    badan
    1.66
    Act Density 0.164%

    No Known Activations