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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    The neuron detects words containing the suffix “ant,” especially chemical‐agent or functional nouns ending in “ant.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    <Product
    -0.07
     renders
    -0.07
     alas
    -0.06
    scratch
    -0.06
     rendered
    -0.06
    unread
    -0.06
     Another
    -0.06
     disrespectful
    -0.06
    ?option
    -0.06
     Lightweight
    -0.06
    POSITIVE LOGITS
    ecom
    0.07
     inspectors
    0.07
     Nietzsche
    0.07
    чих
    0.06
    �
    0.06
    (__
    0.06
     транспор
    0.06
    воб
    0.06
    cor
    0.06
     melody
    0.06
    Act Density 0.030%

    No Known Activations