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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grave
    -0.07
    .workspace
    -0.06
     yup
    -0.06
     com
    -0.06
     зай
    -0.06
    Fair
    -0.06
    iframe
    -0.06
    redo
    -0.06
     болезни
    -0.06
     一般
    -0.06
    POSITIVE LOGITS
    丹
    0.06
    _Game
    0.06
     Paths
    0.06
    ět
    0.06
    _Settings
    0.06
     yearly
    0.06
    -Class
    0.06
    Campaign
    0.06
     compelling
    0.06
    APPER
    0.06
    Act Density 0.016%

    No Known Activations