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

    Neuronpedia

    INDEX
    Explanations

    having

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    271
    -0.07
     RUNNING
    -0.07
     GOOD
    -0.07
     Cyprus
    -0.07
     churn
    -0.06
    SearchTree
    -0.06
     BigDecimal
    -0.06
     deaf
    -0.06
    -good
    -0.06
     Hampshire
    -0.06
    POSITIVE LOGITS
     sucess
    0.08
     vụ
    0.07
    вай
    0.06
    上海
    0.06
    ního
    0.06
    机关
    0.06
    이를
    0.06
     vestib
    0.06
     också
    0.06
    (userData
    0.06
    Act Density 0.151%

    No Known Activations