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

    Neuronpedia

    INDEX
    Explanations

    references to heavy metals and related terminology

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

    heavy adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.50
    euvres
    -0.45
    WindowConstants
    -0.45
    RequestMapping
    -0.45
    paddingVertical
    -0.44
     Pinocchio
    -0.43
    Elise
    -0.43
    atuor
    -0.43
     Solskjaer
    -0.43
    rset
    -0.43
    POSITIVE LOGITS
     Heavy
    1.20
    Heavy
    1.17
    heavy
    1.09
     heavy
    1.04
     HEAVY
    0.98
     pesados
    0.83
     pesado
    0.82
     pesada
    0.81
     lourd
    0.71
     heaviest
    0.69
    Act Density 0.008%

    No Known Activations