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

    Neuronpedia

    INDEX
    Explanations

    hungry for suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    다
    0.61
    ا
    0.53
    机器人
    0.51
    ా
    0.49
    льный
    0.48
    ulador
    0.47
    ę
    0.47
    вы
    0.46
    슈
    0.46
    לק
    0.46
    POSITIVE LOGITS
     Hemp
    0.54
     Clarke
    0.51
     Holloway
    0.48
     Feet
    0.46
    ftone
    0.46
     uppermost
    0.46
     nostrils
    0.46
     Frye
    0.45
     toes
    0.45
     seams
    0.45
    Act Density 0.002%

    No Known Activations