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

    Neuronpedia

    INDEX
    Explanations

    PR followed by rounded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Física
    0.53
     př
    0.52
     Jó
    0.51
     libre
    0.50
     Arbe
    0.50
    Begriff
    0.47
    komm
    0.47
    FindingsResponse
    0.47
     tuli
    0.47
    Mapa
    0.46
    POSITIVE LOGITS
    eal
    0.68
    reated
    0.66
    ounding
    0.64
    ound
    0.64
    eep
    0.63
    aking
    0.63
    reat
    0.62
    riving
    0.62
    ean
    0.61
    ot
    0.60
    Act Density 0.110%

    No Known Activations