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

    Neuronpedia

    INDEX
    Explanations

    programming syntax elements related to control structures and options

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

    code block syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.52
    MessageState
    -0.43
     betweenstory
    -0.38
    Diweddarwch
    -0.38
    principalColumn
    -0.36
     dAtA
    -0.35
     ::=
    -0.32
     itemprop
    -0.31
    numerusform
    -0.30
    bewerken
    -0.30
    POSITIVE LOGITS
    SharedCtor
    0.65
    :✨
    0.56
    出版年
    0.55
     InputDecoration
    0.54
     ligiloj
    0.53
    ModelAdmin
    0.51
    jspb
    0.51
    Jeografia
    0.49
    Derbyniad
    0.48
    pfel
    0.48
    Act Density 0.107%

    No Known Activations