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

    Neuronpedia

    INDEX
    Explanations

    is definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carefree
    0.63
     със
    0.62
     ஆராய்ச்ச
    0.60
     lucrative
    0.59
     helplessly
    0.58
     cowboys
    0.58
    ilfe
    0.57
    全新的
    0.57
     ništa
    0.57
    ህል
    0.57
    POSITIVE LOGITS
     είναι
    0.69
     varies
    0.67
     differs
    0.66
     была
    0.65
     wynosi
    0.65
     depends
    0.63
     oraz
    0.62
     була
    0.62
     (
    0.61
     ήταν
    0.61
    Act Density 0.038%

    No Known Activations