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

    Neuronpedia

    INDEX
    Explanations

    converting units and formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    かの
    0.42
    into
    0.38
     wi
    0.37
    erd
    0.37
    iderm
    0.36
    Into
    0.35
    haz
    0.35
    Ok
    0.35
    derd
    0.35
    тово
    0.35
    POSITIVE LOGITS
     ನೋಡ
    0.42
     generales
    0.42
    ialis
    0.41
     relâche
    0.40
     quotients
    0.39
    cèle
    0.39
     VISION
    0.39
     Показа
    0.38
     semelhante
    0.38
    وري
    0.38
    Act Density 0.001%

    No Known Activations