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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on all-caps C/C++ identifiers and macro names (tokens consisting of uppercase letters and underscores).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    reward
    -0.07
    variation
    -0.07
     Alison
    -0.07
    eceğiz
    -0.06
    ệu
    -0.06
    WORK
    -0.06
     employers
    -0.06
    text
    -0.06
     symbols
    -0.06
     article
    -0.06
    POSITIVE LOGITS
     мик
    0.06
     мой
    0.06
    ัญช
    0.06
     않는
    0.06
    htmlspecialchars
    0.06
     सह
    0.06
    NameValuePair
    0.06
    @d
    0.06
    -dd
    0.06
     пох
    0.06
    Act Density 0.049%

    No Known Activations