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

    Neuronpedia

    INDEX
    Explanations

    goalkeeper saves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wiring
    0.44
    Wiring
    0.41
     политика
    0.41
    disamb
    0.39
    acceleration
    0.38
    particles
    0.38
    fired
    0.38
    astri
    0.38
     पॉलिट
    0.38
     Wiring
    0.37
    POSITIVE LOGITS
     goalkeeper
    1.26
     goalie
    1.24
     keeper
    1.13
     goalt
    1.10
     keepers
    1.05
     Keeper
    0.99
    🧤
    0.87
    keeper
    0.79
     saves
    0.79
    Keeper
    0.77
    Act Density 0.004%

    No Known Activations