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

    Neuronpedia

    INDEX
    Explanations

    website code

    np_max-act · gemini-2.0-flash

    This neuron mainly responds to HTML/XML closing‐tag tokens (e.g. “</div>”, “</head>”, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (temp
    -0.06
     Properties
    -0.06
    诺
    -0.06
    .restaurant
    -0.06
     जम
    -0.06
    _PARAMS
    -0.06
    닝
    -0.06
    .publish
    -0.06
    	gbc
    -0.06
    _deriv
    -0.06
    POSITIVE LOGITS
     Alumni
    0.07
    REDENTIAL
    0.06
     तस
    0.06
    กำ
    0.06
     NotFound
    0.06
    Sc
    0.06
     Hunger
    0.06
    ylv
    0.06
    スク
    0.06
    Senior
    0.06
    Act Density 0.012%

    No Known Activations