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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слоя
    -0.09
     layers
    -0.08
     Shaft
    -0.08
    éns
    -0.08
     Layers
    -0.08
    িমান
    -0.08
    reh
    -0.08
    理念
    -0.07
    ens
    -0.07
     субъ
    -0.07
    POSITIVE LOGITS
     matchup
    0.15
    Scheduled
    0.11
    Upcoming
    0.11
     scheduled
    0.11
     Scheduled
    0.11
    cheduled
    0.10
     مباراة
    0.10
    CHEDULE
    0.10
    Opponent
    0.10
    scheduled
    0.10
    Act Density 0.147%

    No Known Activations