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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wnętrz
    -0.08
    shop
    -0.07
    .btnClose
    -0.07
     carr
    -0.07
    חלק
    -0.07
    ools
    -0.07
     ofApp
    -0.07
    antine
    -0.07
     '.',
    -0.07
     upstairs
    -0.07
    POSITIVE LOGITS
    管理者
    0.07
     formidable
    0.07
     bloody
    0.07
    notifications
    0.06
    лист
    0.06
    Restore
    0.06
    productive
    0.06
    osed
    0.06
    のも
    0.06
     yo
    0.06
    Act Density 0.057%

    No Known Activations