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

    Neuronpedia

    INDEX
    Explanations

    code and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жность
    0.43
    馄
    0.40
    윗
    0.40
    强度
    0.40
    oxet
    0.40
    ிற்கும்
    0.40
    bulk
    0.39
    맥
    0.39
    ровку
    0.39
    ność
    0.39
    POSITIVE LOGITS
     ಒಂದು
    0.42
     alleviating
    0.40
     relaxation
    0.40
     freeing
    0.39
     forming
    0.39
     augmenting
    0.38
     explorations
    0.38
     една
    0.38
     एक
    0.38
     batteries
    0.38
    Act Density 0.000%

    No Known Activations