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

    Neuronpedia

    INDEX
    Explanations

    internet access

    np_max-act · gemini-2.0-flash

    The neuron activates on terms related to network access and connectivity, such as “access,” “connect,” and “provider.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    NULL
    -0.07
     tas
    -0.07
    melon
    -0.06
    .decorate
    -0.06
     TL
    -0.06
    DataType
    -0.06
    EATURE
    -0.06
    REGION
    -0.06
    CA
    -0.06
     kitchen
    -0.06
    POSITIVE LOGITS
    ateur
    0.07
     findById
    0.07
     belum
    0.07
     /:
    0.07
    _tensors
    0.06
     yPos
    0.06
     steadily
    0.06
    าจ
    0.06
    .pages
    0.06
    preh
    0.06
    Act Density 0.029%

    No Known Activations