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

    Neuronpedia

    INDEX
    Explanations

    display image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engaging
    0.67
     relaxing
    0.62
     Engaging
    0.62
    ीजन
    0.61
     open
    0.61
    중
    0.61
    ្នក
    0.61
     borg
    0.60
    翟
    0.60
     Gérard
    0.60
    POSITIVE LOGITS
    scatter
    0.91
     Scatter
    0.85
     scatter
    0.83
    Scatter
    0.82
    movement
    0.79
    imshow
    0.77
     उत्पादों
    0.77
     scattered
    0.74
     Fog
    0.73
    辛
    0.73
    Act Density 0.001%

    No Known Activations