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

    Neuronpedia

    INDEX
    Explanations

    non- context / non- player

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कर्ताओं
    0.44
     frå
    0.42
    েন
    0.42
     Paul
    0.40
    building
    0.40
     എന്നാല്‍
    0.39
     Proto
    0.39
     Tiene
    0.39
     svoje
    0.38
    hey
    0.38
    POSITIVE LOGITS
     extensible
    0.54
     избежать
    0.49
     inextric
    0.47
     hectares
    0.46
     supercritical
    0.45
     unskilled
    0.45
     exquisitely
    0.45
     tassels
    0.45
     photocurrent
    0.44
     spacious
    0.44
    Act Density 0.000%

    No Known Activations