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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and control flow elements

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

    Code block ending keywords

    np_acts-logits-general · gemini-2.0-flash

    programming loop endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    return
    -0.70
     return
    -0.65
     Returns
    -0.62
     Return
    -0.61
     Returning
    -0.60
    Returning
    -0.59
     returning
    -0.58
     returns
    -0.57
     returned
    -0.57
    Return
    -0.56
    POSITIVE LOGITS
     endforeach
    0.85
    endforeach
    0.81
     endfor
    0.78
    endfor
    0.78
    IsMutable
    0.69
    ftagPool
    0.68
    :+:
    0.65
    endwhile
    0.64
    saraba
    0.64
    NOPQRST
    0.64
    Act Density 0.041%

    No Known Activations