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

    Neuronpedia

    INDEX
    Explanations

    structural elements of code, particularly parts of method and class definitions

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code definitions and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.84
     $_"
    -0.82
     pylint
    -0.82
     itſelf
    -0.80
    ientras
    -0.80
    neſs
    -0.79
    eſt
    -0.78
     -->>
    -0.78
    nefs
    -0.77
    >\<^
    -0.76
    POSITIVE LOGITS
    <eos>
    1.09
    ↵
    0.92
     ...
    0.88
    ↵↵
    0.80
    ↵↵↵↵
    0.78
    ↵↵↵
    0.77
    ...
    0.74
    }
    0.74
    </em>
    0.71
    ......
    0.69
    Act Density 0.170%

    No Known Activations