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

    Neuronpedia

    INDEX
    Explanations

    Private

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “private.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Eck
    -0.06
    ^[
    -0.06
     Beck
    -0.06
     Cox
    -0.06
     Transformer
    -0.06
     hỗ
    -0.06
     Thorn
    -0.06
     Egg
    -0.06
     Bow
    -0.06
    Oh
    -0.06
    POSITIVE LOGITS
     private
    0.15
     Private
    0.14
    private
    0.14
    Private
    0.12
    	private
    0.12
     PRIVATE
    0.10
    -private
    0.09
    (private
    0.09
     privately
    0.08
    .Private
    0.08
    Act Density 0.026%

    No Known Activations