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

    Neuronpedia

    INDEX
    Explanations

    specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ESSIONS
    0.38
    nite
    0.37
    ẹ
    0.37
    檢查
    0.36
    עים
    0.36
    idos
    0.36
    ári
    0.36
    ợp
    0.36
    概
    0.36
    监
    0.36
    POSITIVE LOGITS
    具体的な
    0.46
    理由は
    0.44
     detailed
    0.43
     details
    0.43
    理由
    0.43
     linguaggio
    0.42
    Detailed
    0.42
     detay
    0.42
    の詳細
    0.41
     Detailed
    0.41
    Act Density 0.546%

    No Known Activations