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

    Neuronpedia

    INDEX
    Explanations

    comment syntax in code documentation

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

    MSBuild database operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    -0.54
    いれば
    -0.46
     quæ
    -0.46
    ième
    -0.46
    ు
    -0.43
    tlere
    -0.42
    യും
    -0.42
     nuoc
    -0.41
    ر
    -0.41
     Cosby
    -0.40
    POSITIVE LOGITS
    */
    1.35
    <bos>
    0.69
    */
    0.67
    })();
    0.59
    )))
    0.58
    }));
    0.54
     GenerationType
    0.54
    jwa
    0.54
    Eleg
    0.53
     CreateTagHelper
    0.53
    Act Density 0.001%

    No Known Activations