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

    Neuronpedia

    INDEX
    Explanations

    saving and copying files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ดำเนินการ
    0.41
     oublier
    0.39
    disable
    0.39
    0.38
    getBase
    0.38
     dizendo
    0.37
     encephal
    0.37
     préalable
    0.36
    iguez
    0.36
    WhiteRatingDiff
    0.36
    POSITIVE LOGITS
     copy
    0.74
     Copy
    0.73
     saving
    0.68
    Copy
    0.68
     copying
    0.66
     Save
    0.66
     копи
    0.66
    Save
    0.65
    copy
    0.64
     save
    0.63
    Act Density 0.003%

    No Known Activations