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

    Neuronpedia

    INDEX
    Explanations

    updates to services/products

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     себ
    -0.06
    ��드
    -0.06
    .isPlaying
    -0.06
     ARC
    -0.06
    ignant
    -0.06
     ank
    -0.06
    。那
    -0.06
     '')↵
    -0.06
    ใช
    -0.06
     {?
    -0.06
    POSITIVE LOGITS
    Sigma
    0.07
    Express
    0.06
    (decimal
    0.06
    0.06
    rigesimal
    0.06
    	token
    0.06
     Showcase
    0.06
    ﾌ
    0.06
    왕
    0.06
    _paper
    0.06
    Act Density 0.095%

    No Known Activations