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

    Neuronpedia

    INDEX
    Explanations

    name, image, automating, clumsy, brave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.63
     இங்கு
    0.49
    lowski
    0.49
    ante
    0.48
    AutoGen
    0.48
    p
    0.47
     devant
    0.46
    finaly
    0.46
     जुड़े
    0.46
     continueRoutine
    0.46
    POSITIVE LOGITS
    微
    0.50
    烏
    0.49
    轉
    0.45
    擾
    0.45
    忍
    0.45
    ρον
    0.44
    ární
    0.43
    ညာ
    0.43
    0.43
    жно
    0.43
    Act Density 0.001%

    No Known Activations