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

    Neuronpedia

    INDEX
    Explanations

    measurements and facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سره
    0.47
    の位置
    0.47
     endeavoured
    0.46
    ี
    0.45
     AppMethodBeat
    0.44
    的车
    0.44
    少し
    0.43
     pamph
    0.43
     DISPLAYS
    0.43
    ্দ
    0.43
    POSITIVE LOGITS
    engelsk
    0.51
    ome
    0.49
    one
    0.49
    anya
    0.49
    ensk
    0.49
    hyp
    0.48
    appen
    0.48
    yoga
    0.48
    hung
    0.48
    ang
    0.48
    Act Density 0.001%

    No Known Activations