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

    Neuronpedia

    INDEX
    Explanations

    various forms of return statements in code

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

    return statements in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.73
    Rohy
    -0.73
    ſſung
    -0.71
    RectangleBorder
    -0.70
    <unused74>
    -0.70
    <pad>
    -0.70
    <unused68>
    -0.70
     deſſen
    -0.70
    <unused14>
    -0.70
    [@BOS@]
    -0.70
    POSITIVE LOGITS
    .
    0.38
     because
    0.30
     때문
    0.30
    beginPath
    0.28
    ;
    0.28
    return
    0.27
    printStackTrace
    0.26
     but
    0.25
     importanza
    0.24
     Ursache
    0.24
    Act Density 0.006%

    No Known Activations