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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structured elements in code snippets

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

    code symbols and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.48
    ünst
    -0.47
     esternos
    -0.41
    sweise
    -0.38
    CGContext
    -0.38
     democrática
    -0.38
    KURZBESCHREIBUNG
    -0.37
     pylint
    -0.37
    شنگ
    -0.37
    bakter
    -0.37
    POSITIVE LOGITS
    :✨
    0.53
    ParallelGroup
    0.49
    Obrázky
    0.48
     فريبيس
    0.48
     imageNamed
    0.46
     whichever
    0.44
     EconPapers
    0.43
    цездатний
    0.42
     nød
    0.40
    DockStyle
    0.40
    Act Density 0.183%

    No Known Activations