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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML/XML markup tokens (angle-bracketed tags and delimiters).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     meny
    -0.06
     srp
    -0.06
    nave
    -0.06
    Issuer
    -0.06
    INCLUDE
    -0.06
     slander
    -0.06
    _NUMERIC
    -0.06
    림
    -0.06
    ifikace
    -0.06
     прос
    -0.06
    POSITIVE LOGITS
     xuống
    0.07
     shortcut
    0.07
    getDefault
    0.07
     softened
    0.06
    _processing
    0.06
    Tutorial
    0.06
    _pi
    0.06
     pert
    0.06
    actus
    0.06
     crystall
    0.06
    Act Density 0.008%

    No Known Activations