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

    Neuronpedia

    INDEX
    Explanations

    dice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BT
    -0.07
    КА
    -0.07
     Mirror
    -0.07
    _annotations
    -0.06
     кос
    -0.06
     WORLD
    -0.06
     ส
    -0.06
    =tk
    -0.06
     neighbors
    -0.06
    مند
    -0.06
    POSITIVE LOGITS
     dice
    0.07
     Wi
    0.06
     homework
    0.06
     extensive
    0.06
     vole
    0.06
     відбувається
    0.06
     disrespectful
    0.06
    蛋
    0.06
    위
    0.06
    asley
    0.06
    Act Density 0.005%

    No Known Activations