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

    Neuronpedia

    INDEX
    Explanations

    created / produced / released / built

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stochastic
    0.50
     cursory
    0.49
     hany
    0.47
     may
    0.46
    uestos
    0.46
     pressione
    0.45
     MNIST
    0.44
    わかる
    0.44
     recorr
    0.44
     irresponsible
    0.43
    POSITIVE LOGITS
     whose
    0.96
    whose
    0.89
     الذي
    0.85
     που
    0.81
     که
    0.77
    ที่
    0.76
     التي
    0.75
    ที่มี
    0.74
    which
    0.73
     cuyas
    0.71
    Act Density 0.163%

    No Known Activations