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

    Neuronpedia

    INDEX
    Explanations

    focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decap
    0.44
     quadru
    0.43
    それでも
    0.42
     semelhantes
    0.41
     molde
    0.40
     seres
    0.39
     totales
    0.39
     bons
    0.39
     увели
    0.39
     sixth
    0.38
    POSITIVE LOGITS
    üler
    0.47
    בש
    0.46
    ামো
    0.44
    ot
    0.44
     Rä
    0.43
     কেবল
    0.43
    gä
    0.43
     Battles
    0.43
     發
    0.42
     카드
    0.42
    Act Density 0.001%

    No Known Activations