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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ial or -ium"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ort
    -0.07
    óst
    -0.07
     chứa
    -0.07
    ליק
    -0.06
    兄
    -0.06
    끙
    -0.06
    起き
    -0.06
     chờ
    -0.06
     найти
    -0.06
    -op
    -0.06
    POSITIVE LOGITS
    娴
    0.08
    Schema
    0.07
     Beacon
    0.07
     unveiled
    0.07
    (Xml
    0.07
    🚣
    0.06
    Scenario
    0.06
     Chains
    0.06
     wielding
    0.06
    NullPointerException
    0.06
    Act Density 0.001%

    No Known Activations