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

    Neuronpedia

    INDEX
    Explanations

    code blocks or structures related to conditional logic and loops

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

    Code blocks or code-related content

    np_acts-logits-general · gemini-2.0-flash

    else and otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ENBERG
    -0.64
    ")));
    -0.62
     """
    -0.61
    "):
    -0.60
    )";
    -0.57
    ++
    -0.57
     star
    -0.56
     screenWidth
    -0.56
     codes
    -0.56
    =?";
    -0.55
    POSITIVE LOGITS
    else
    0.80
     else
    0.79
     Else
    0.76
     Otherwise
    0.68
    Otherwise
    0.67
     OTHERWISE
    0.64
    }
    0.64
    },
    0.63
     otherwise
    0.62
    Else
    0.61
    Act Density 0.083%

    No Known Activations