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

    Neuronpedia

    INDEX
    Explanations

    www

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viso
    0.61
    serializing
    0.60
     sienta
    0.58
    招待
    0.57
    эх
    0.54
     எதி
    0.53
    ज्ञा
    0.52
     ability
    0.51
    祝い
    0.51
     wcex
    0.51
    POSITIVE LOGITS
     www
    0.73
     dot
    0.71
    wwww
    0.64
    www
    0.63
     Deputy
    0.58
    DOT
    0.57
    lL
    0.57
    .??
    0.57
    dot
    0.55
     PPC
    0.55
    Act Density 0.007%

    No Known Activations