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

    Neuronpedia

    INDEX
    Explanations

    references to magnets and magnetic materials

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

    magnet poles and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.50
     './
    -0.44
    ../../
    -0.44
     ``
    -0.44
    исленность
    -0.43
     Cau
    -0.42
    //--
    -0.41
     Cruz
    -0.40
    PARSE
    -0.40
    hö
    -0.40
    POSITIVE LOGITS
    Magnet
    1.09
    magnet
    1.08
     magnet
    1.02
     Magnet
    0.99
     magnets
    0.88
     desmotivaciones
    0.75
    Personensuche
    0.70
     enfans
    0.67
     juges
    0.66
     MAGNET
    0.66
    Act Density 0.006%

    No Known Activations