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

    Neuronpedia

    INDEX
    Explanations

    orders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sa
    -0.07
    DefaultValue
    -0.07
     Bởi
    -0.07
     BaseController
    -0.07
    _Is
    -0.07
    Endian
    -0.07
    重要内容
    -0.07
    沉浸
    -0.07
     Damian
    -0.07
     المباراة
    -0.07
    POSITIVE LOGITS
    committed
    0.08
    Ws
    0.07
     shaving
    0.07
    .des
    0.07
    hor
    0.07
    LOB
    0.07
    UND
    0.07
    jid
    0.07
     neighbor
    0.07
    LL
    0.07
    Act Density 0.001%

    No Known Activations