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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron detects polite user requests phrased as questions, especially those beginning with "Could you".

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    恨
    -0.06
     debates
    -0.06
     Перв
    -0.06
     nghe
    -0.06
     �
    -0.06
    ."','".$
    -0.06
    像是
    -0.06
     formed
    -0.06
     yararlan
    -0.06
    令
    -0.05
    POSITIVE LOGITS
    IMITIVE
    0.07
    >V
    0.07
     कर
    0.06
     Zen
    0.06
    ordan
    0.06
     Vib
    0.06
    *B
    0.06
    .getWidth
    0.06
    _exp
    0.06
    .subplots
    0.06
    Act Density 0.021%

    No Known Activations