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

    Neuronpedia

    INDEX
    Explanations

    controller server

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of Kubernetes control‐plane component names (e.g. “kube-controller-manager,” “kube-scheduler,” “kube-apiserver,” “kube-proxy”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Александ
    -0.06
     gums
    -0.06
     apk
    -0.06
     RequestOptions
    -0.06
    /login
    -0.06
    .Models
    -0.06
    .aws
    -0.06
     ultimately
    -0.06
     died
    -0.06
     το
    -0.06
    POSITIVE LOGITS
    _ver
    0.07
     crist
    0.07
     frontal
    0.06
    -floor
    0.06
     पढ़
    0.06
     Pur
    0.06
     göl
    0.06
     Taxi
    0.06
     specials
    0.06
    vic
    0.06
    Act Density 0.003%

    No Known Activations