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

    Neuronpedia

    INDEX
    Explanations

    correct answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.43
     realize
    0.41
     breeders
    0.41
     longtime
    0.40
     towers
    0.40
     __
    0.39
     Obr
    0.39
     enth
    0.39
     READY
    0.39
     prices
    0.39
    POSITIVE LOGITS
    leyball
    0.49
    odef
    0.49
     అనంతరం
    0.48
    冂
    0.47
    uninstall
    0.46
    ина
    0.46
    thisStudent
    0.45
    ື່
    0.45
    걷
    0.45
     разру
    0.44
    Act Density 0.007%

    No Known Activations