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

    Neuronpedia

    INDEX
    Explanations

    specific programming and coding terminology within a technical context

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

    special characters and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.81
    новништво
    -0.81
     kasarigan
    -0.79
    -0.72
    таратура
    -0.68
    Autoritní
    -0.68
     оригіналу
    -0.67
    ロウィン
    -0.66
    ագրություններ
    -0.65
     autorytatywna
    -0.65
    POSITIVE LOGITS
     recall
    0.29
     }));
    0.28
     }))
    0.28
     posesión
    0.26
     זו
    0.26
     sujetos
    0.25
     romántica
    0.25
    .),
    0.25
     inoltre
    0.25
    $/,
    0.25
    Act Density 0.009%

    No Known Activations