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

    Neuronpedia

    INDEX
    Explanations

    specific classifications and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蛋白质
    0.42
    رو
    0.42
    ută
    0.42
    вата
    0.40
    带动
    0.40
    nými
    0.39
     inny
    0.39
    nas
    0.39
    မာ
    0.38
    电话
    0.38
    POSITIVE LOGITS
     fully
    0.45
    VENTORY
    0.44
     COST
    0.43
    ২১
    0.43
     Clarity
    0.42
     OP
    0.42
    Interpret
    0.42
     Interpret
    0.42
     Equilibrium
    0.42
     Hastings
    0.40
    Act Density 0.001%

    No Known Activations