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

    Neuronpedia

    INDEX
    Explanations

    customs clearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deswegen
    0.86
     toda
    0.82
    ల్
    0.81
     созда
    0.79
     собственно
    0.78
    tokens
    0.77
     চির
    0.75
     corriendo
    0.75
    тифика
    0.75
     график
    0.74
    POSITIVE LOGITS
    【
    0.96
    謝
    0.95
    It
    0.92
     eczema
    0.91
    ן
    0.91
    Ph
    0.90
    י
    0.90
    有用
    0.90
    يلي
    0.90
    ל
    0.90
    Act Density 0.003%

    No Known Activations