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

    Neuronpedia

    INDEX
    Explanations

    references to private entities or concepts

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

    "private"

    np_acts-logits-general · gemini-2.0-flash

    private

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.54
     ddelwed
    -0.51
     Teg
    -0.51
     consultato
    -0.51
     laſſen
    -0.51
    ੝
    -0.50
    SharedCtor
    -0.50
    ătoare
    -0.50
    anting
    -0.50
    licitations
    -0.50
    POSITIVE LOGITS
     sector
    0.56
    Private
    0.54
     Private
    0.51
     私
    0.42
    private
    0.40
     PRIVATE
    0.40
     privat
    0.39
     privati
    0.39
    PRIVATE
    0.39
     Privat
    0.39
    Act Density 0.077%

    No Known Activations