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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron is picking up on numeric literals written with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ford
    -0.08
     annotate
    -0.07
     MCP
    -0.07
     Ford
    -0.06
    Changing
    -0.06
    (selected
    -0.06
    belt
    -0.06
     corporation
    -0.06
    Test
    -0.06
     constitutional
    -0.06
    POSITIVE LOGITS
    getString
    0.08
     αρι
    0.07
    589
    0.07
    >>)
    0.07
     getString
    0.07
    objectManager
    0.06
    arms
    0.06
    Valor
    0.06
    ває
    0.06
    Characters
    0.06
    Act Density 0.003%

    No Known Activations