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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gwen
    -0.07
     manifests
    -0.07
     secara
    -0.06
    (b
    -0.06
     Britann
    -0.06
     brut
    -0.06
     مربع
    -0.06
     równ
    -0.06
     Rein
    -0.06
     Dont
    -0.06
    POSITIVE LOGITS
     alignItems
    0.08
    ンズ
    0.08
    ます
    0.07
     CharSet
    0.07
    .GetAxis
    0.07
    Executing
    0.07
    тер
    0.07
     рад
    0.06
    _:*
    0.06
    езпеч
    0.06
    Act Density 0.078%

    No Known Activations