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

    Neuronpedia

    INDEX
    Explanations

    can experiment, download, build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impatience
    0.74
     చేస్త
    0.72
    初回
    0.71
     Suprema
    0.68
    webElement
    0.67
    ente
    0.67
     numberWith
    0.67
     szczę
    0.65
     ആദ്യ
    0.65
    ிலி
    0.64
    POSITIVE LOGITS
     easily
    2.44
     facilement
    2.09
     Easily
    2.02
     fácilmente
    2.01
    easily
    2.01
     facilmente
    1.94
     بسه
    1.89
     आसानी
    1.77
     freely
    1.73
     effortlessly
    1.71
    Act Density 0.612%

    No Known Activations