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

    Neuronpedia

    INDEX
    Explanations

    taste, colour

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    omid
    0.64
     ngại
    0.59
    safe
    0.55
     sécur
    0.54
    댄
    0.54
    ían
    0.53
     হ্যা
    0.52
    त्रे
    0.52
    DAN
    0.51
    fa
    0.51
    POSITIVE LOGITS
     flavours
    0.73
     sauerkraut
    0.66
     sempat
    0.65
     shows
    0.64
     medall
    0.64
    Ⴝ
    0.63
     colours
    0.63
     colouring
    0.61
     Moskau
    0.61
     bought
    0.61
    Act Density 0.000%

    No Known Activations