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

    Neuronpedia

    INDEX
    Explanations

    name beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tuple
    0.42
     Colombeau
    0.42
     ഉപകരണ
    0.41
     Elytres
    0.40
     copyspace
    0.40
     VStack
    0.40
     DSLR
    0.40
     Fleurit
    0.40
     anisot
    0.40
     Reverso
    0.40
    POSITIVE LOGITS
    ina
    0.58
    ia
    0.57
    ita
    0.56
    islav
    0.56
    ika
    0.55
    isha
    0.53
    ie
    0.52
    berto
    0.51
     Michael
    0.51
    ida
    0.50
    Act Density 0.026%

    No Known Activations