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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures and leaders

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

    historical figures and leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.58
    CascadeType
    -0.56
    COUVER
    -0.51
     EconPapers
    -0.51
     RouterModule
    -0.51
    SequentialGroup
    -0.48
    Liefs
    -0.47
     JAXBElement
    -0.47
    exitRule
    -0.47
     terciopelo
    -0.46
    POSITIVE LOGITS
     esternos
    0.37
     saint
    0.36
     Sie
    0.33
     nonUne
    0.32
    mort
    0.32
     Saint
    0.32
    imedes
    0.32
    mor
    0.30
     muerto
    0.29
     Gou
    0.29
    Act Density 0.171%

    No Known Activations