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

    Neuronpedia

    INDEX
    Explanations

    complex technical subjects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yesu
    0.46
    繰り返し
    0.46
     یہودیوں
    0.46
    «
    0.45
    の中で
    0.45
    Crawler
    0.44
    の関係
    0.44
    異なる
    0.43
    <<
    0.43
    あるいは
    0.43
    POSITIVE LOGITS
     hebdom
    0.83
     cogniz
    0.75
     peculiarly
    0.75
     volition
    0.73
     erstwhile
    0.72
     effectual
    0.72
     aloof
    0.71
     alleviation
    0.67
     assemblage
    0.66
     galore
    0.65
    Act Density 0.006%

    No Known Activations