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

    Neuronpedia

    INDEX
    Explanations

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    َ
    0.44
     Brownian
    0.43
    Pourquoi
    0.43
    사
    0.42
     Recherche
    0.42
    Ỗ
    0.41
    ЗА
    0.41
     お客様
    0.41
     オーバー
    0.40
    يف
    0.40
    POSITIVE LOGITS
    //
    0.42
    тни
    0.41
    ↵↵
    0.41
     inoltre
    0.40
     altri
    0.40
    addPreferred
    0.38
    /*
    0.38
    //{
    0.38
    することも
    0.36
     cursory
    0.36
    Act Density 0.026%

    No Known Activations