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

    Neuronpedia

    INDEX
    Explanations

    Role

    np_max-act · gemini-2.0-flash

    The neuron activates on the appearance of Kubernetes RBAC resource type names—particularly “Role,” “ClusterRole,” and “Binding.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     eru
    -0.06
     týd
    -0.06
    -types
    -0.06
    enderror
    -0.06
    ��
    -0.06
     було
    -0.06
     billeder
    -0.06
    &id
    -0.06
     lässt
    -0.06
    617
    -0.06
    POSITIVE LOGITS
    .transfer
    0.07
    Resistance
    0.06
     رد
    0.06
    Unlock
    0.06
     Seeking
    0.06
     sorumlu
    0.06
    .Document
    0.06
    "label
    0.06
     scrolls
    0.06
    love
    0.06
    Act Density 0.002%

    No Known Activations