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

    Neuronpedia

    INDEX
    Explanations

    loops and control flow structures, particularly "while" statements

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

    Keywords indicating time or duration

    np_acts-logits-general · gemini-2.0-flash

    while loop conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.77
    NameInMap
    -0.71
    ConstraintMaker
    -0.69
    AutoresizingMask
    -0.64
    featureID
    -0.63
    Hochspringen
    -0.63
     AssemblyTitle
    -0.62
    >[]
    -0.59
    providedIn
    -0.58
     AspNetCore
    -0.57
    POSITIVE LOGITS
     till
    0.73
    Till
    0.73
     until
    0.68
     Until
    0.63
     Till
    0.62
    Until
    0.62
     til
    0.60
     동안
    0.58
     True
    0.58
    until
    0.56
    Act Density 0.026%

    No Known Activations