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

    Neuronpedia

    INDEX
    Explanations

    significant achievements or rankings in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Placement, finishing, or runner-up in a competition

    np_acts-logits-general · gemini-2.0-flash

    finishing positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTCX
    -0.73
    DrawerToggle
    -0.53
     trajets
    -0.51
    かね
    -0.47
    bitField
    -0.43
    simp
    -0.42
    tamount
    -0.42
     vol
    -0.41
     simpl
    -0.41
     onOptions
    -0.41
    POSITIVE LOGITS
     runner
    1.37
     runners
    1.15
     finish
    1.06
     finishes
    1.04
     Runner
    1.04
     placing
    1.03
    runner
    1.02
     finishing
    1.01
     Runners
    0.96
     placement
    0.95
    Act Density 0.104%

    No Known Activations