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 is sensitive to uppercase programming or query keywords (e.g. SQL commands like PREPARE, FROM, AS).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     подум
    -0.06
     yours
    -0.06
    .arguments
    -0.06
    _Button
    -0.06
    _RESPONSE
    -0.06
    	bar
    -0.06
    -sensitive
    -0.06
    شود
    -0.06
    638
    -0.06
     жен
    -0.06
    POSITIVE LOGITS
     cudd
    0.06
    ="__
    0.06
     santé
    0.06
     sel
    0.06
    asons
    0.06
    iron
    0.06
    ським
    0.06
     eviction
    0.06
     diren
    0.06
     -
    0.06
    Act Density 0.048%

    No Known Activations