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

    Neuronpedia

    INDEX
    Explanations

    criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assertion
    -0.07
     nap
    -0.07
    uni
    -0.07
    UserService
    -0.06
    но
    -0.06
     pulses
    -0.06
     TOUCH
    -0.06
    (Return
    -0.06
     spouse
    -0.06
    üre
    -0.06
    POSITIVE LOGITS
     больш
    0.07
     CART
    0.06
     orta
    0.06
    )','
    0.06
     Mitsubishi
    0.06
     издел
    0.06
    malink
    0.06
     BorderLayout
    0.06
    ổng
    0.06
     advocating
    0.06
    Act Density 0.004%

    No Known Activations