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

    Neuronpedia

    INDEX
    Explanations

    wave quality and break types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surfing
    1.14
     surfer
    1.11
     surfers
    1.10
     surfboard
    1.04
     surf
    1.02
     Surf
    1.00
    surfing
    0.99
    Surf
    0.95
    surf
    0.93
    🏄
    0.80
    POSITIVE LOGITS
     spilling
    0.55
     peel
    0.54
     peaks
    0.52
     reeling
    0.52
     hollow
    0.51
     spill
    0.49
     peels
    0.49
     peeling
    0.49
     barrels
    0.48
     dump
    0.48
    Act Density 0.005%

    No Known Activations