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

    Neuronpedia

    INDEX
    Explanations

    never ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Datas
    0.48
     Dictionary
    0.46
     Sinf
    0.45
     Pu
    0.44
     Schema
    0.43
     Real
    0.42
     Stem
    0.42
     elaborado
    0.42
     Horticultural
    0.42
     dese
    0.41
    POSITIVE LOGITS
     nikdy
    0.52
    never
    0.49
    marca
    0.48
    ЕНИ
    0.47
     lakini
    0.47
    nije
    0.46
    nes
    0.46
     никогда
    0.46
     aldrig
    0.45
    Nunca
    0.45
    Act Density 0.010%

    No Known Activations