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

    Neuronpedia

    INDEX
    Explanations

    fig

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    9
    0.79
    ۹
    0.79
    ٩
    0.66
    ９
    0.61
    ⁹
    0.61
     कीमतें
    0.60
    फोन
    0.59
    ペーン
    0.58
     agrícolas
    0.57
     affer
    0.56
    POSITIVE LOGITS
    e
    0.80
    LL
    0.79
    ER
    0.76
    ED
    0.76
    ed
    0.75
     fig
    0.72
    Z
    0.72
    ா
    0.66
    a
    0.66
    Edu
    0.66
    Act Density 0.001%

    No Known Activations