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

    Neuronpedia

    INDEX
    Explanations

    pass through / conflicts without / country code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ு
    1.61
    ে
    1.41
     danos
    1.34
    و
    1.33
    သိ
    1.25
    housing
    1.21
     مقاله
    1.19
     yeni
    1.18
     beneficios
    1.18
     كبير
    1.16
    POSITIVE LOGITS
    𝚒
    1.38
    𝐢
    1.32
    𝐞
    1.27
    𝐤
    1.26
    𝐧
    1.24
    Colorful
    1.23
    denom
    1.23
    𝐅
    1.23
    né
    1.21
    நபியே
    1.19
    Act Density 0.000%

    No Known Activations