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

    Neuronpedia

    INDEX
    Explanations

    arm and subsequent words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fn
    0.42
     toes
    0.41
    年后
    0.41
    ❉
    0.41
     Feet
    0.40
    <0x1C>
    0.39
    清洁
    0.39
    మన
    0.39
    of
    0.39
    清理
    0.39
    POSITIVE LOGITS
     Arm
    0.96
    Arm
    0.93
     arm
    0.93
    arm
    0.78
     ARM
    0.65
    adillo
    0.62
    臂
    0.61
     Armin
    0.61
     arme
    0.59
    pits
    0.59
    Act Density 0.008%

    No Known Activations