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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ाह
    -0.08
    .ContentType
    -0.07
     نماید
    -0.07
    变化
    -0.07
    ibble
    -0.07
     kancel
    -0.06
     YT
    -0.06
    opathy
    -0.06
    िथ
    -0.06
    (formatter
    -0.06
    POSITIVE LOGITS
     aph
    0.06
     ammonia
    0.06
     Flame
    0.06
     İzmir
    0.06
     Contrib
    0.06
     Dag
    0.06
    \Backend
    0.06
     Blond
    0.06
    ponsored
    0.06
    	header
    0.06
    Act Density 0.018%

    No Known Activations