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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brittle
    -0.06
    Early
    -0.06
    Unlike
    -0.06
     сут
    -0.06
     marches
    -0.06
     hauling
    -0.06
     Fam
    -0.06
    /",↵
    -0.06
    لعاب
    -0.06
    .While
    -0.06
    POSITIVE LOGITS
     İzmir
    0.07
    .optString
    0.07
    "sync
    0.07
    \Queue
    0.07
    dad
    0.07
    brief
    0.07
     Invasion
    0.06
    HttpGet
    0.06
    　 　 　 　 　 　
    0.06
     Enrique
    0.06
    Act Density 0.024%

    No Known Activations