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

    Neuronpedia

    INDEX
    Explanations

    recognition

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect the phrase and concept “speech recognition.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (player
    -0.07
    _fig
    -0.07
    出版
    -0.07
     Fern
    -0.07
    
    -0.06
    _intersection
    -0.06
    續
    -0.06
    ียด
    -0.06
     trust
    -0.06
    Pa
    -0.06
    POSITIVE LOGITS
    _EXT
    0.07
     bik
    0.07
    PERTIES
    0.06
    asher
    0.06
    (cin
    0.06
    anners
    0.06
    arine
    0.06
    Seq
    0.06
    аних
    0.06
     Threshold
    0.06
    Act Density 0.006%

    No Known Activations