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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on programming code syntax, identifying source‐code tokens and structures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     робота
    -0.06
    ि
    -0.06
    ）:
    -0.06
    ائه
    -0.06
     \
    -0.06
     stabilized
    -0.06
    centaje
    -0.06
    ')}
    -0.06
    insi
    -0.05
     livro
    -0.05
    POSITIVE LOGITS
    ModelIndex
    0.07
    (Context
    0.07
     Interested
    0.07
    InvalidArgumentException
    0.07
    _ops
    0.07
    ABI
    0.07
    hon
    0.06
    _FAMILY
    0.06
    .vaadin
    0.06
     Mobility
    0.06
    Act Density 2.574%

    No Known Activations