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

    Neuronpedia

    INDEX
    Explanations

    code complexity

    np_max-act · gemini-2.0-flash

    This neuron identifies HTML/XML tags and other angle‐bracket-delimited markup elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .HorizontalAlignment
    -0.07
    _Pin
    -0.06
    安
    -0.05
    _RUNTIME
    -0.05
     ceremonies
    -0.05
     βιβ
    -0.05
    .mb
    -0.05
     Miy
    -0.05
    iomanip
    -0.05
    _timestamp
    -0.05
    POSITIVE LOGITS
     Fight
    0.07
     Assassin
    0.07
     ऊपर
    0.07
    던
    0.06
    」「
    0.06
     digging
    0.06
     skyline
    0.06
     ре
    0.06
    _term
    0.06
     battle
    0.06
    Act Density 0.005%

    No Known Activations