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

    Neuronpedia

    INDEX
    Explanations

    multi-part symbols or expressions often used in technical or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numeric or symbolic prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     թվական
    -0.58
     måned
    -0.43
     idéia
    -0.42
    enumii
    -0.42
     Feinde
    -0.41
     Grüsse
    -0.40
     ơn
    -0.40
     hôtes
    -0.39
     nachhal
    -0.39
    kuuta
    -0.39
    POSITIVE LOGITS
    WireFormatLite
    0.60
    OGND
    0.52
    #+#
    0.52
    ItemClick
    0.43
     Exacts
    0.41
    CodedInputStream
    0.41
     propOrder
    0.40
    richTextPanel
    0.39
    transQ
    0.38
    titch
    0.37
    Act Density 0.096%

    No Known Activations