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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fora
    -0.06
    kills
    -0.06
    (.)
    -0.06
    куля
    -0.06
    dir
    -0.06
     Pizza
    -0.06
    次数
    -0.05
     так
    -0.05
    _SB
    -0.05
     institutional
    -0.05
    POSITIVE LOGITS
     passport
    0.07
    _Instance
    0.07
     eru
    0.07
     totalPrice
    0.06
     doll
    0.06
     Vault
    0.06
     Passenger
    0.06
    (nonatomic
    0.06
     une
    0.06
    0.06
    Act Density 0.009%

    No Known Activations