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

    Neuronpedia

    INDEX
    Explanations

    terms related to directives and commands in programming contexts

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

    rectifier, direct, straight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.40
    ⓘ
    -0.39
     ciudadana
    -0.39
     getItemCount
    -0.39
    IContainer
    -0.38
     instalação
    -0.36
    ellido
    -0.35
     renon
    -0.34
    }{*}{}
    -0.34
    MemoryWarning
    -0.33
    POSITIVE LOGITS
     пря
    1.30
     straight
    1.23
     Straight
    1.23
    straight
    1.23
    Пря
    1.20
    Straight
    1.17
    Direct
    1.17
     прямо
    1.16
    direct
    1.13
     прямой
    1.09
    Act Density 0.011%

    No Known Activations