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

    Neuronpedia

    INDEX
    Explanations

    calculate radius, distance from center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.75
    v
    0.75
    0.74
    呐
    0.71
    祈
    0.68
    kort
    0.67
    cena
    0.67
     discoloration
    0.66
    −
    0.66
    (
    0.66
    POSITIVE LOGITS
    پلز
    0.96
     dettag
    0.90
     esegu
    0.89
     dettaglio
    0.88
     articolo
    0.88
     sehari
    0.85
    ㅇ
    0.83
     párrafo
    0.80
     piuttosto
    0.80
    swagen
    0.79
    Act Density 0.000%

    No Known Activations