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

    Neuronpedia

    INDEX
    Explanations

    functional programming constructs and control flow statements

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

    Code that includes "ret" or "return"

    np_acts-logits-general · gemini-2.0-flash

    return or ret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Haig
    -0.60
     Tula
    -0.57
     STAN
    -0.56
     Breeze
    -0.55
     EDD
    -0.52
    Gust
    -0.49
     Sla
    -0.49
    Wad
    -0.49
    Dougall
    -0.49
     Gust
    -0.48
    POSITIVE LOGITS
    ret
    2.83
     ret
    2.82
     Ret
    2.63
    Ret
    2.56
     RET
    2.28
    RET
    2.12
     retreat
    1.59
     retra
    1.58
     Retreat
    1.54
    rets
    1.49
    Act Density 0.175%

    No Known Activations