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

    Neuronpedia

    INDEX
    Explanations

    engine parts and combustion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cocoa
    0.50
    膚
    0.44
    狗
    0.41
     Obesity
    0.41
     obesidad
    0.40
     childish
    0.40
    肤
    0.39
     Sozial
    0.39
     telehealth
    0.39
     Psychological
    0.38
    POSITIVE LOGITS
     cylinder
    1.97
     cylinders
    1.88
     Cylinder
    1.69
    cylinder
    1.68
     combustion
    1.59
     piston
    1.59
     цилинд
    1.57
     pistons
    1.54
     cilind
    1.48
     crankshaft
    1.48
    Act Density 0.027%

    No Known Activations