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

    Neuronpedia

    INDEX
    Explanations

    Material (unknown/not specified)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    আ
    1.34
    Κ
    1.32
    Α
    1.25
    ア
    1.20
     Ä
    1.18
    紝
    1.17
    1.16
     जागे
    1.14
    Т
    1.14
     Embroidery
    1.11
    POSITIVE LOGITS
    والفقار
    1.29
    ło
    1.25
    ութ
    1.25
    ्तीय
    1.22
     saab
    1.20
    یز
    1.19
    hurst
    1.18
     geç
    1.17
    yb
    1.16
    вые
    1.15
    Act Density 0.000%

    No Known Activations