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

    Neuronpedia

    INDEX
    Explanations

    conditional statements in programming code

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

    if then return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.85
    IntoConstraints
    -0.76
    MLLoader
    -0.69
     AttributeSet
    -0.68
    hoeddwyd
    -0.66
     endforeach
    -0.65
     $_"
    -0.65
    ImageContext
    -0.64
     informée
    -0.63
    majánló
    -0.61
    POSITIVE LOGITS
     accelerate
    0.38
     acceleration
    0.37
     NEVER
    0.34
     action
    0.34
     less
    0.34
     stay
    0.34
     during
    0.34
     now
    0.34
     durumda
    0.33
     menos
    0.33
    Act Density 0.036%

    No Known Activations