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

    Neuronpedia

    INDEX
    Explanations

    website generators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يد
    1.25
    ાર્
    1.25
     আদালত
    1.22
    ীব
    1.21
    াণী
    1.18
     traz
    1.17
     gráfica
    1.17
    ुरी
    1.16
    л
    1.16
     largura
    1.14
    POSITIVE LOGITS
    et
    1.20
    gcc
    1.19
    punct
    1.15
    blit
    1.13
    gings
    1.13
    gpt
    1.12
    gib
    1.09
    伀
    1.09
     antic
    1.08
    geist
    1.07
    Act Density 0.081%

    No Known Activations