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

    Neuronpedia

    INDEX
    Explanations

    or, option, choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cknowledg
    0.40
    শ্বাস
    0.40
    水の
    0.40
    innitus
    0.39
     nejen
    0.38
    鱧
    0.38
    தையும்
    0.38
     niacin
    0.38
    ♰
    0.38
    чив
    0.38
    POSITIVE LOGITS
     veya
    0.60
     oppure
    0.59
     yoki
    0.58
     seçenek
    0.55
     또는
    0.54
     Apakah
    0.53
     හෝ
    0.52
     escolher
    0.51
     wählen
    0.50
     หรือ
    0.50
    Act Density 1.213%

    No Known Activations