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

    Neuronpedia

    INDEX
    Explanations

    enter

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals (especially decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .SystemColors
    -0.07
    MaxY
    -0.06
    _game
    -0.06
     آمده
    -0.06
    Pawn
    -0.06
    арх
    -0.06
     condolences
    -0.06
     Pix
    -0.06
     covariance
    -0.06
    .dp
    -0.06
    POSITIVE LOGITS
     zpět
    0.07
    WITHOUT
    0.07
     Syntax
    0.07
     nikdo
    0.07
     ENTER
    0.07
     výraz
    0.06
     correct
    0.06
     �
    0.06
    (Value
    0.06
     Ans
    0.06
    Act Density 0.024%

    No Known Activations