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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures related to expressions in programming languages

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

    expressions in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.63
     kasarigan
    -0.60
    DockStyle
    -0.54
    ymce
    -0.53
     democrática
    -0.50
    WithIOException
    -0.50
    SharedDtor
    -0.50
    PageFactory
    -0.49
    oldest
    -0.48
    fitrión
    -0.48
    POSITIVE LOGITS
     expression
    0.67
     equation
    0.65
    expression
    0.61
    Expression
    0.60
     expressions
    0.59
     Expression
    0.59
     Equation
    0.59
     Expr
    0.56
    expr
    0.56
     expr
    0.56
    Act Density 0.014%

    No Known Activations