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

    Neuronpedia

    INDEX
    Explanations

    need something, requests going, to comply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ينه
    0.38
    доби
    0.37
    最新的
    0.37
     setNew
    0.37
     beck
    0.36
    incs
    0.35
     newer
    0.35
    វែង
    0.35
     Newer
    0.35
     magn
    0.34
    POSITIVE LOGITS
     같
    0.42
    dalam
    0.40
    咉
    0.39
     wśród
    0.38
    modelLogin
    0.38
     khen
    0.38
    บริเวณ
    0.37
     Selv
    0.37
     trait
    0.37
     Traits
    0.37
    Act Density 0.001%

    No Known Activations