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

    Neuronpedia

    INDEX
    Explanations

    Questions and instructions

    np_max-act · gemini-2.0-flash

    This neuron activates on Spanish-language words (especially common verbs) in user queries, effectively detecting when the text is in Spanish.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     precondition
    -0.06
     wed
    -0.06
     Xi
    -0.06
     hn
    -0.06
    //****************************************************************
    -0.06
    党
    -0.06
    Double
    -0.06
     业
    -0.06
     cắt
    -0.06
    ands
    -0.06
    POSITIVE LOGITS
    TRANS
    0.06
    haf
    0.06
                                    
    0.06
    .volley
    0.06
    IgnoreCase
    0.06
    ерп
    0.06
     perpetrator
    0.06
     iconName
    0.06
    Playback
    0.06
     DIFF
    0.06
    Act Density 0.098%

    No Known Activations