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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ru
    -0.08
     absorbed
    -0.08
     negligence
    -0.07
     involved
    -0.07
     petals
    -0.06
     emphas
    -0.06
    /Users
    -0.06
     decay
    -0.06
     blond
    -0.06
     contracts
    -0.06
    POSITIVE LOGITS
    uez
    0.07
     '')
    0.06
     الان
    0.06
    Xml
    0.06
    leDb
    0.06
    atchewan
    0.06
    Space
    0.06
    ;")↵
    0.06
    kor
    0.06
    _mouse
    0.06
    Act Density 0.025%

    No Known Activations