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

    Neuronpedia

    INDEX
    Explanations

    rules and policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Disposition
    -0.07
    "What
    -0.06
     pursuit
    -0.06
     सरक
    -0.06
     остров
    -0.06
     enterprise
    -0.06
    American
    -0.06
     clinic
    -0.06
     黑
    -0.06
    PagerAdapter
    -0.06
    POSITIVE LOGITS
    opo
    0.07
     eyeb
    0.07
     Processes
    0.06
    uces
    0.06
     FindObjectOfType
    0.06
    Gay
    0.06
     obsc
    0.06
    (vertex
    0.06
    زی
    0.06
    िह
    0.06
    Act Density 0.002%

    No Known Activations