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

    Neuronpedia

    INDEX
    Explanations

    human body

    np_acts-logits-general · gemini-2.5-flash-lite

    physical body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ル
    0.80
    یر
    0.80
    ᱘
    0.77
    用い
    0.76
    ۷
    0.74
    ᱗
    0.73
    ズ
    0.70
    ᱖
    0.70
    ᱐
    0.68
    ма
    0.67
    POSITIVE LOGITS
     (
    0.89
     I
    0.80
    ↵
    0.71
    า
    0.71
     be
    0.69
     CPU
    0.67
     TV
    0.65
     US
    0.65
     OK
    0.65
     UP
    0.63
    Act Density 0.748%

    No Known Activations