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

    Neuronpedia

    INDEX
    Explanations

    Docker

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect Docker‐related terms (e.g., “docker,” “file,” “container,” “containerize”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     McGill
    -0.06
     ей
    -0.06
     Teen
    -0.06
     Parcelable
    -0.06
     GHC
    -0.06
    rices
    -0.06
     Germans
    -0.06
    fec
    -0.06
     діт
    -0.06
     skiing
    -0.06
    POSITIVE LOGITS
     соответствии
    0.07
    adia
    0.07
     lasted
    0.06
    .dense
    0.06
    ادن
    0.06
    \Model
    0.06
    orld
    0.06
    노출
    0.06
     wind
    0.06
     expertise
    0.06
    Act Density 0.013%

    No Known Activations