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

    Neuronpedia

    INDEX
    Explanations

    references to specific intentions or goals behind actions

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

    purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inscrivez
    -0.65
     sereia
    -0.60
     Connectez
    -0.55
    queryInterface
    -0.54
    Morfologia
    -0.52
     bikinis
    -0.52
     handcuffs
    -0.52
     telefónica
    -0.51
     Keuangan
    -0.51
     Händler
    -0.51
    POSITIVE LOGITS
     purposes
    1.96
    purposes
    1.66
     Purposes
    1.63
     purpose
    1.60
     Purpose
    1.52
    Purpose
    1.43
    purpose
    1.41
     PURPOSE
    1.32
    PURPOSE
    1.26
     propósitos
    0.91
    Act Density 0.013%

    No Known Activations