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

    Neuronpedia

    INDEX
    Explanations

    blockquote and code block formatting in the text

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

    Code snippets or markup delimiters

    np_acts-logits-general · gemini-2.0-flash

    describes, Filled, Let

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.62
    躇
    -0.59
    AnimationsModule
    -0.59
     Carsten
    -0.57
    FLD
    -0.56
    roon
    -0.56
    IContainer
    -0.56
    rypt
    -0.56
    lito
    -0.55
    ellyn
    -0.55
    POSITIVE LOGITS
    </blockquote>
    1.09
     Audiodateien
    0.65
    \]
    0.59
     iconLine
    0.59
    </table>
    0.58
    ."""
    0.50
     ModelExpression
    0.50
    }}}}
    0.49
    </h3>
    0.48
    ↵↵↵↵↵↵↵↵↵
    0.48
    Act Density 0.156%

    No Known Activations