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

    Neuronpedia

    INDEX
    Explanations

    effort prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tarifleri
    0.54
     teori
    0.50
     enerji
    0.48
     ogrom
    0.48
    erjee
    0.46
     Pottery
    0.45
     ponieważ
    0.45
    Arts
    0.45
     elektry
    0.45
    യാള
    0.45
    POSITIVE LOGITS
     and
    0.63
    의
    0.46
     및
    0.45
     व
    0.44
    inserts
    0.43
    도
    0.42
     benefits
    0.42
     physicochemical
    0.40
     மற்றும்
    0.40
    and
    0.40
    Act Density 0.004%

    No Known Activations