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

    Neuronpedia

    INDEX
    Explanations

    creating, conversions, celebrating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rumours
    0.48
     illa
    0.48
     Mining
    0.47
     lobortis
    0.46
     vodi
    0.45
     Raster
    0.44
     jackpot
    0.44
     monstru
    0.44
     DOES
    0.44
     humana
    0.44
    POSITIVE LOGITS
    Holder
    0.47
    holders
    0.46
    pl
    0.45
    holder
    0.43
    D
    0.42
    Bened
    0.41
    стую
    0.40
    Celebrating
    0.40
    р
    0.40
     предстоя
    0.40
    Act Density 0.000%

    No Known Activations