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

    Neuronpedia

    INDEX
    Explanations

    cd to project directory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‒
    1.93
    ITÉ
    1.86
    ،
    1.76
     أس
    1.74
    、「
    1.72
    さまざまな
    1.71
    ──
    1.69
    そのため
    1.69
    、《
    1.67
     poiché
    1.65
    POSITIVE LOGITS
     alot
    2.20
     goin
    1.89
     bbq
    1.75
     atleast
    1.69
     युवाओ
    1.68
     kinda
    1.67
     loosing
    1.67
    꺽
    1.62
     কারন
    1.62
     tuff
    1.61
    Act Density 0.514%

    No Known Activations