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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superiority
    -0.07
    -kit
    -0.07
    克
    -0.07
    -rise
    -0.07
     righteousness
    -0.07
    루
    -0.06
     возраст
    -0.06
    ournament
    -0.06
    ーブ
    -0.06
     कम
    -0.06
    POSITIVE LOGITS
    ند
    0.07
     Codable
    0.06
    Pri
    0.06
    )&&(
    0.06
    unting
    0.06
    _supply
    0.06
     isNaN
    0.06
     banda
    0.06
     Tyr
    0.06
     Αυ
    0.06
    Act Density 0.005%

    No Known Activations