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

    Neuronpedia

    INDEX
    Explanations

    words related to equipment or gear

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

    gear changes and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Milton
    -0.47
     ''
    -0.46
    an
    -0.44
     (
    -0.43
     Malone
    -0.42
    onDelete
    -0.41
     human
    -0.41
     Masson
    -0.41
     Racine
    -0.40
     )(
    -0.40
    POSITIVE LOGITS
     gear
    2.14
    Gear
    1.90
     Gear
    1.90
    gear
    1.86
     GEAR
    1.69
    GEAR
    1.68
    ギア
    1.13
     Ausrüstung
    1.05
    gears
    0.95
     gears
    0.93
    Act Density 0.005%

    No Known Activations