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

    Neuronpedia

    INDEX
    Explanations

    Physical actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝐙
    -0.08
     ghetto
    -0.08
    .Interfaces
    -0.08
    짱
    -0.07
    客栈
    -0.07
    页面
    -0.07
    EventData
    -0.07
     enclave
    -0.07
     Endpoint
    -0.07
    如果不
    -0.07
    POSITIVE LOGITS
    ости
    0.08
    役
    0.07
     Just
    0.07
    ascar
    0.07
    anger
    0.06
    glich
    0.06
    られ
    0.06
    PackageManager
    0.06
    avery
    0.06
    gets
    0.06
    Act Density 0.006%

    No Known Activations