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

    Neuronpedia

    INDEX
    Explanations

    albeit unusual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <
    0.42
    ton
    0.42
    <'
    0.41
     L
    0.40
     Mind
    0.40
    with
    0.39
     with
    0.39
     Greatest
    0.39
     ngũ
    0.38
     තර
    0.38
    POSITIVE LOGITS
    荕
    0.46
    祅
    0.42
     ইসলামিক
    0.42
    枤
    0.42
    uosa
    0.42
     حرام
    0.41
    篂
    0.40
    われています
    0.40
    connection
    0.39
     нещо
    0.39
    Act Density 0.011%

    No Known Activations