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

    Neuronpedia

    INDEX
    Explanations

    code elements that indicate return statements in programming contexts

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

    return values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.98
    AndEndTag
    -0.82
    Cyfarwyddwr
    -0.79
     الرياضيه
    -0.78
    NameInMap
    -0.77
     autorytatywna
    -0.76
    <unused74>
    -0.75
    <unused28>
    -0.75
    <unused14>
    -0.75
    <unused8>
    -0.74
    POSITIVE LOGITS
    return
    0.48
     return
    0.47
     Derfor
    0.39
     them
    0.35
     therefore
    0.34
     derfor
    0.34
     somit
    0.32
    จึง
    0.32
     
    0.32
     returns
    0.31
    Act Density 0.014%

    No Known Activations