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

    Neuronpedia

    INDEX
    Explanations

    adding

    np_max-act · gemini-2.0-flash

    The neuron fires on code that dynamically injects or appends HTML (e.g. via jQuery’s append/innerHTML/AJAX‐insert operations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     alliance
    -0.07
     wars
    -0.07
    tk
    -0.06
     Wars
    -0.06
    	version
    -0.06
    част
    -0.06
     над
    -0.06
    ANDROID
    -0.06
    aurus
    -0.06
     thresh
    -0.06
    POSITIVE LOGITS
    inject
    0.07
    ...,
    0.07
     LIMITED
    0.07
    StringValue
    0.07
     говорит
    0.07
    -host
    0.07
     grö
    0.07
     Killing
    0.06
    .Int
    0.06
    Clar
    0.06
    Act Density 0.032%

    No Known Activations