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

    Neuronpedia

    INDEX
    Explanations

    Core frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opening
    0.73
    ço
    0.70
    }">
    0.69
     utilizzato
    0.69
    看板
    0.68
     opening
    0.67
     çö
    0.67
    ToWrite
    0.67
    交換
    0.66
     exchange
    0.65
    POSITIVE LOGITS
    ケル
    0.69
     даст
    0.66
    磷
    0.65
    MLE
    0.65
     જી
    0.65
    ЕМ
    0.64
    egas
    0.64
    ем
    0.64
     കണ
    0.63
    溦
    0.63
    Act Density 0.001%

    No Known Activations