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

    Neuronpedia

    INDEX
    Explanations

    Help

    np_max-act · gemini-2.0-flash

    The neuron detects HTML markup syntax, particularly angle-bracket tag delimiters (e.g. “<…>” and “</…>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _creator
    -0.07
    .initial
    -0.07
    gif
    -0.07
     boil
    -0.07
     prevState
    -0.07
    English
    -0.07
    	result
    -0.06
    Subjects
    -0.06
    _pdf
    -0.06
    _started
    -0.06
    POSITIVE LOGITS
     Moines
    0.08
    .ComponentModel
    0.08
     Renault
    0.07
     McM
    0.07
    venues
    0.07
     interpolated
    0.06
     sym
    0.06
    Miss
    0.06
     annihil
    0.06
         ↵↵
    0.06
    Act Density 0.001%

    No Known Activations