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

    Neuronpedia

    INDEX
    Explanations

    /etc/ configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oğlu
    0.93
    ᓴ
    0.91
    /
    0.91
     наличие
    0.86
    зму
    0.86
    дел
    0.86
     tentatives
    0.85
    Trying
    0.85
    ូល
    0.83
     Trying
    0.83
    POSITIVE LOGITS
     │
    0.86
     chronological
    0.84
    ដំណ
    0.82
     مدت
    0.81
    …,
    0.79
     magistrate
    0.79
    脑袋
    0.79
    ├
    0.78
    {}".
    0.77
    лая
    0.77
    Act Density 0.041%

    No Known Activations