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

    Neuronpedia

    INDEX
    Explanations

    met

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “met” when it appears in license‐style comment blocks (e.g. the “met:” line introducing conditions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crib
    -0.08
    　　　　
    -0.07
    adı
    -0.07
     trùng
    -0.06
    Hint
    -0.06
    .cell
    -0.06
     Soup
    -0.06
     again
    -0.06
    　　　　 　
    -0.06
     dividend
    -0.06
    POSITIVE LOGITS
    рош
    0.08
    机
    0.07
    Eat
    0.07
    说
    0.07
    alers
    0.06
    monic
    0.06
    ニメ
    0.06
     orden
    0.06
     حالة
    0.06
     processo
    0.06
    Act Density 0.001%

    No Known Activations