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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egative
    -0.08
     Pret
    -0.08
    付费
    -0.07
    rots
    -0.07
    dü
    -0.07
    .orders
    -0.07
     Lester
    -0.07
    doubleValue
    -0.07
     kittens
    -0.07
     AtomicInteger
    -0.06
    POSITIVE LOGITS
    隶属于
    0.07
     обы
    0.07
    调解
    0.07
     Agent
    0.06
    (Matrix
    0.06
    izu
    0.06
    ali
    0.06
    .rf
    0.06
    广播
    0.06
    سلح
    0.06
    Act Density 0.022%

    No Known Activations