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

    Neuronpedia

    INDEX
    Explanations

    invoice confirmation number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ד
    3.05
    s
    2.33
    ्स
    2.19
    sh
    2.08
    ો
    2.08
    t
    1.96
    𝗲
    1.94
    nd
    1.92
    ્સ
    1.90
    u
    1.90
    POSITIVE LOGITS
    ৬
    1.91
    GA
    1.86
     Belgi
    1.82
    PSK
    1.79
    ЛИ
    1.77
     toad
    1.77
     VGA
    1.74
    раст
    1.74
    NEL
    1.73
     fooled
    1.72
    Act Density 0.067%

    No Known Activations