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

    Neuronpedia

    INDEX
    Explanations

    physical actions with body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    流程
    0.40
     übernommen
    0.39
     धमाल
    0.39
     évolution
    0.39
     സൃഷ്ട
    0.38
     গড়ে
    0.37
     algorithms
    0.37
    戮
    0.37
     عوامل
    0.36
    without
    0.36
    POSITIVE LOGITS
     his
    0.45
     mustache
    0.43
     své
    0.42
     pogled
    0.42
    т
    0.42
     kembali
    0.40
     savo
    0.39
    Sunglasses
    0.39
     рукой
    0.39
     его
    0.39
    Act Density 0.057%

    No Known Activations