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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash

    The neuron activates on terms describing low‐level code optimization and search algorithms (e.g. “using,” “binary,” “search,” “optimize”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     TextInputType
    -0.06
    UG
    -0.06
     calibration
    -0.06
     Us
    -0.06
     Consumers
    -0.06
     Healing
    -0.06
    ATTER
    -0.06
    parameters
    -0.06
    けれど
    -0.06
    iforn
    -0.06
    POSITIVE LOGITS
     percept
    0.07
    พย
    0.07
     lời
    0.07
     혹
    0.06
    ній
    0.06
    Cit
    0.06
     interested
    0.06
    _LOCAL
    0.06
     slashed
    0.06
    现
    0.06
    Act Density 0.026%

    No Known Activations