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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric data—particularly multi-digit numbers and decimals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     navCtrl
    -0.07
    �
    -0.07
     Towards
    -0.07
    ाकर
    -0.07
     Lý
    -0.07
     全
    -0.06
     naar
    -0.06
    ernes
    -0.06
    rowave
    -0.06
    POSITIVE LOGITS
     addition
    0.10
     listen
    0.07
     nást
    0.07
     listens
    0.07
     punt
    0.07
     Highland
    0.07
     допомаг
    0.07
     Listen
    0.07
    Similar
    0.07
     assisted
    0.07
    Act Density 0.018%

    No Known Activations