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

    Neuronpedia

    INDEX
    Explanations

    suggest

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    所
    0.73
     назад
    0.68
    ്യ
    0.66
     ન
    0.66
     বি
    0.66
     न
    0.65
     сов
    0.64
     now
    0.64
    กี
    0.63
    onitrile
    0.63
    POSITIVE LOGITS
     recomend
    0.68
     直接
    0.68
    来る
    0.67
     Crescent
    0.66
     jurispr
    0.66
     diretta
    0.65
     directamente
    0.64
    StateToProps
    0.64
    推薦
    0.63
     deren
    0.63
    Act Density 0.029%

    No Known Activations