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

    Neuronpedia

    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     axis
    0.49
     angle
    0.46
     intervals
    0.45
     ask
    0.44
     expectancy
    0.43
     amps
    0.43
     recesses
    0.42
     embeds
    0.42
     Colombe
    0.41
     asks
    0.41
    POSITIVE LOGITS
     произ
    0.49
    gypte
    0.48
     entstanden
    0.47
    uchtigkeit
    0.47
     χρει
    0.46
     }^{
    0.45
     नरम
    0.45
    akta
    0.45
     passeio
    0.45
     પસંદ
    0.44
    Act Density 0.002%

    No Known Activations