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

    Neuronpedia

    INDEX
    Explanations

    building and accumulating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puertos
    0.52
     destac
    0.50
    ی
    0.46
    ת
    0.46
    的市场
    0.46
     destaque
    0.45
     destacados
    0.45
     élément
    0.45
     אות
    0.44
     ultimatum
    0.43
    POSITIVE LOGITS
     Canterbury
    0.48
    =
    0.47
    rak
    0.46
     meat
    0.46
    =-
    0.46
    =%
    0.46
     Therapy
    0.46
    .
    0.45
    fish
    0.44
     therapy
    0.44
    Act Density 0.008%

    No Known Activations