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

    Neuronpedia

    INDEX
    Explanations

    instructions related to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Least
    0.43
    Best
    0.42
     poorest
    0.40
    Poor
    0.40
    America
    0.39
    Effective
    0.39
    ondi
    0.38
     −
    0.38
    Oh
    0.38
    Bel
    0.37
    POSITIVE LOGITS
    navigation
    0.41
    进化
    0.39
     मेवा
    0.38
    덬
    0.38
    parties
    0.38
    ការព
    0.37
    suppliers
    0.37
     cavern
    0.37
    зья
    0.37
     straining
    0.37
    Act Density 0.001%

    No Known Activations