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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron fires on the version‐number tokens in Kubernetes manifest “apiVersion” fields (e.g. the “apps/v1” parts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Millenn
    -0.07
    baz
    -0.07
    �
    -0.07
    ileaks
    -0.06
     Ivanka
    -0.06
    ▍
    -0.06
    oplay
    -0.06
    aycast
    -0.06
     Genre
    -0.06
     Mistress
    -0.06
    POSITIVE LOGITS
     queryInterface
    0.07
     springs
    0.06
    .place
    0.06
    createView
    0.06
     counters
    0.06
    φι
    0.06
    аб
    0.06
    #create
    0.06
     getPlayer
    0.06
    (Object
    0.06
    Act Density 0.001%

    No Known Activations