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

    Neuronpedia

    INDEX
    Explanations

    every step of the way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nip
    0.37
    worldly
    0.36
     kle
    0.35
     Ips
    0.35
    ﻝ
    0.34
    間の
    0.34
    }%
    0.34
     गेंदों
    0.34
    रन
    0.33
    アイ
    0.33
    POSITIVE LOGITS
    ყო
    0.44
     streaming
    0.35
     Serrano
    0.35
    驹
    0.35
    velo
    0.34
     bamb
    0.34
     {{
    0.34
    েন্ড
    0.34
    &=
    0.33
     Claude
    0.33
    Act Density 0.002%

    No Known Activations