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

    Neuronpedia

    INDEX
    Explanations

    references to privacy and personal ownership

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

    private or dedicated aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dernières
    -0.52
     keç
    -0.51
     pesada
    -0.47
     esprits
    -0.46
     činnosti
    -0.45
     amarillas
    -0.45
     intéressante
    -0.44
     navideñas
    -0.44
     últimas
    -0.43
     hipótesis
    -0.43
    POSITIVE LOGITS
     own
    0.55
    WithIOException
    0.53
    DockStyle
    0.52
    extAlignment
    0.51
     privacy
    0.50
     secluded
    0.49
     OWN
    0.48
     private
    0.47
     PRIVACY
    0.46
     nahilalakip
    0.46
    Act Density 0.002%

    No Known Activations