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

    Neuronpedia

    INDEX
    Explanations

    stunt performer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మీడియా
    0.51
    音频
    0.42
    Video
    0.41
    Projekt
    0.40
    álním
    0.37
    Purple
    0.37
    喈
    0.37
    プロジェクト
    0.37
    Project
    0.36
    빔
    0.36
    POSITIVE LOGITS
     stunt
    0.84
     doubles
    0.80
     doubled
    0.73
     doubling
    0.73
     stunts
    0.71
     Doubles
    0.66
     doubl
    0.56
     double
    0.54
    dou
    0.54
     dou
    0.51
    Act Density 0.014%

    No Known Activations