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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     {'
    -0.06
    _directory
    -0.06
    Song
    -0.06
    -field
    -0.06
    _policy
    -0.06
     Attention
    -0.06
    function
    -0.06
     buds
    -0.06
    mask
    -0.06
    POSITIVE LOGITS
     Erect
    0.07
     �
    0.07
    .RE
    0.07
     annonces
    0.07
     L
    0.07
    (IN
    0.07
     замі
    0.07
    	pre
    0.07
     겁
    0.06
     toute
    0.06
    Act Density 0.080%

    No Known Activations