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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    束
    -0.08
    scape
    -0.08
     sermons
    -0.08
     ulaş
    -0.07
    foreach
    -0.07
     campuses
    -0.07
    clusters
    -0.07
    unwrap
    -0.07
    spur
    -0.07
     backlinks
    -0.07
    POSITIVE LOGITS
    双方
    0.15
     ఇద్ద
    0.12
    (players
    0.12
    玩家
    0.11
     ಇಬ್ಬ
    0.11
     ставки
    0.11
     partisan
    0.11
     jugadores
    0.11
     taruhan
    0.11
     खेल
    0.10
    Act Density 0.026%

    No Known Activations