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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron detects XML/HTML/XML-plist markup delimiters, i.e. the angle-bracket tags and their structural tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    label
    -0.07
    μο
    -0.06
    boru
    -0.06
    Islam
    -0.06
    aed
    -0.06
    _SENS
    -0.06
    ("[
    -0.06
    overlap
    -0.06
    volt
    -0.06
     invo
    -0.06
    POSITIVE LOGITS
     nouvelle
    0.07
    ENAME
    0.07
     fc
    0.06
     проф
    0.06
     και
    0.06
     unexpectedly
    0.06
     neurop
    0.06
     DESCRIPTION
    0.06
     Security
    0.06
     personally
    0.06
    Act Density 0.003%

    No Known Activations