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

    Neuronpedia

    INDEX
    Explanations

    implementation

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on occurrences of the word “implementation” in code comments and documentation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     دوست
    -0.06
     sky
    -0.06
     Fox
    -0.06
    _read
    -0.06
    電視
    -0.06
     العربية
    -0.06
    اسر
    -0.06
    fluid
    -0.06
     Races
    -0.06
     rebels
    -0.06
    POSITIVE LOGITS
     lineup
    0.08
    makta
    0.07
    程度
    0.07
    졌
    0.07
    ladık
    0.07
     ním
    0.07
     Harding
    0.06
     kont
    0.06
     出
    0.06
     reconc
    0.06
    Act Density 0.008%

    No Known Activations