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

    Neuronpedia

    INDEX
    Explanations

    skills for routing and plotting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     잡
    0.43
     선
    0.41
     mentorship
    0.39
    धू
    0.39
     destructor
    0.39
     믿
    0.39
    卍
    0.39
    Discord
    0.38
     restauration
    0.38
     знай
    0.38
    POSITIVE LOGITS
    setScale
    0.45
    eye
    0.44
    aban
    0.43
    karma
    0.39
    inning
    0.39
    variant
    0.38
    நிதி
    0.38
    तम
    0.37
    entities
    0.37
    grams
    0.37
    Act Density 0.000%

    No Known Activations