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

    Neuronpedia

    INDEX
    Explanations

    the name "Jose" or its variations

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

    Jose followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.52
     Wikiseite
    -0.50
    InputModule
    -0.48
     australiano
    -0.46
    mapStateToProps
    -0.46
    cyklopedia
    -0.46
    TNT
    -0.46
    Ukraine
    -0.45
     africaine
    -0.45
     scolaire
    -0.45
    POSITIVE LOGITS
     Jose
    1.88
    Jose
    1.59
     José
    1.59
     JOSE
    1.44
    José
    1.40
     jose
    1.38
    JOSE
    1.25
    jose
    1.23
     JOSÉ
    1.22
     josé
    1.20
    Act Density 0.003%

    No Known Activations