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 activates on programming‐language declaration keywords (e.g. import, public, class, int, interface).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fifty
    -0.08
     Performing
    -0.07
    655
    -0.07
    ağ
    -0.06
    ümüş
    -0.06
     Powerful
    -0.06
    oman
    -0.06
    تی
    -0.06
     ninety
    -0.06
     Kom
    -0.06
    POSITIVE LOGITS
    (parseInt
    0.06
    geb
    0.06
    ाएग
    0.06
     yatır
    0.06
    (HttpStatusCode
    0.06
     (+
    0.06
    _ERROR
    0.06
    "sync
    0.06
    $(".
    0.06
    .converter
    0.06
    Act Density 0.060%

    No Known Activations