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

    Neuronpedia

    INDEX
    Explanations

    opening curly braces in the text

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

    position and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *>
    -0.69
    awtextra
    -0.66
     *)__
    -0.65
     }}</
    -0.65
     }),
    -0.65
     )}$
    -0.65
    ьаж
    -0.65
     }));
    -0.64
     serializers
    -0.64
     })}
    -0.63
    POSITIVE LOGITS
     didalam
    0.64
     feroit
    0.61
     diatas
    0.60
    ammans
    0.55
     enfans
    0.52
     dibawah
    0.52
     poichè
    0.50
     armario
    0.48
    (){}
    0.47
    {
    0.46
    Act Density 0.032%

    No Known Activations