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

    Neuronpedia

    INDEX
    Explanations

    closing braces in the code

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

    code closing blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.92
     الاطلاع
    -0.71
     Geſch
    -0.70
     queſta
    -0.70
    WriteTagHelper
    -0.69
    iſchen
    -0.68
    iſen
    -0.68
    ſſung
    -0.68
    FunctionFlags
    -0.68
    -0.67
    POSITIVE LOGITS
    <eos>
    0.48
    ↵↵
    0.38
    ↵↵↵
    0.37
    ↵
    0.37
    })));
    0.35
    </h2>
    0.34
    }]);
    0.33
    Ver
    0.32
    ↵↵↵↵
    0.31
    </tr>
    0.31
    Act Density 0.001%

    No Known Activations