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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gravity
    -0.07
     Rochester
    -0.07
    WithContext
    -0.06
    RH
    -0.06
    _prev
    -0.06
     Sever
    -0.06
     Oven
    -0.06
     staged
    -0.06
     Avalanche
    -0.06
     artisan
    -0.06
    POSITIVE LOGITS
     didn
    0.07
     doesn
    0.06
     couldn
    0.06
     Москва
    0.06
    (KeyEvent
    0.06
    ти
    0.06
    "]){↵
    0.06
     خارجية
    0.06
    ùa
    0.06
     aren
    0.06
    Act Density 0.041%

    No Known Activations