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

    Neuronpedia

    INDEX
    Explanations

    resources or references mentioned in technical documents

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

    res

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.45
    AsUp
    -0.44
     encontraba
    -0.44
     encuentre
    -0.44
     pueda
    -0.43
     quedado
    -0.42
     trabajado
    -0.42
     quedar
    -0.40
     encontraban
    -0.40
     quedará
    -0.39
    POSITIVE LOGITS
    res
    1.90
     res
    1.85
     Res
    1.65
    Res
    1.63
    RES
    1.31
     RES
    1.27
    ResId
    0.93
     resi
    0.91
     rés
    0.88
     Ress
    0.88
    Act Density 0.002%

    No Known Activations