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

    Neuronpedia

    INDEX
    Explanations

    postcodes and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    7
    0.78
     things
    0.75
    3
    0.73
    6
    0.73
     faces
    0.72
    5
    0.71
     Things
    0.69
    8
    0.69
     Faces
    0.68
    4
    0.66
    POSITIVE LOGITS
    searchDisplay
    0.81
     Hfn
    0.79
     tych
    0.78
    钯
    0.78
     dm
    0.77
    ىلى
    0.77
    $-$,
    0.75
    积分
    0.75
     гг
    0.74
    contentInset
    0.74
    Act Density 0.019%

    No Known Activations