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

    Neuronpedia

    INDEX
    Explanations

    blocks of code or statements that indicate the end of functions or control structures in programming languages

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

    return statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.67
    OGND
    -0.62
     Normdatei
    -0.61
    锈钢
    -0.57
    Rhestr
    -0.56
    ➟
    -0.56
     PeEnEo
    -0.55
    Autoritní
    -0.54
    ſelf
    -0.53
    ſelves
    -0.53
    POSITIVE LOGITS
     whether
    0.44
     wrong
    0.44
    return
    0.37
     zero
    0.36
     however
    0.36
    '.'
    0.36
     AP
    0.35
     $
    0.35
     SOP
    0.35
    WaitGroup
    0.35
    Act Density 0.036%

    No Known Activations