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

    Neuronpedia

    INDEX
    Explanations

    Non-English code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    شاركة
    -0.08
    estors
    -0.08
    tersuch
    -0.08
    føring
    -0.07
    woordig
    -0.07
    راطي
    -0.07
    -filled
    -0.07
     magical
    -0.07
    掉
    -0.07
     lumps
    -0.07
    POSITIVE LOGITS
     announces
    0.09
    텍
    0.08
    UGE
    0.08
     submitting
    0.08
    ugo
    0.08
    Texts
    0.07
     Instances
    0.07
     accompagner
    0.07
     Announces
    0.07
     accolades
    0.07
    Act Density 0.073%

    No Known Activations