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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    The neuron fires on XML/HTML markup structure, i.e. the opening angle‐brackets and tag names in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ymes
    -0.07
    _deg
    -0.07
    dds
    -0.07
    utos
    -0.07
     recherche
    -0.07
    dol
    -0.07
     crab
    -0.07
    ディース
    -0.06
    _DLL
    -0.06
    _MOBILE
    -0.06
    POSITIVE LOGITS
     вій
    0.06
     Kiểm
    0.06
    \Action
    0.06
    alted
    0.06
     condem
    0.06
    Watch
    0.06
     çalış
    0.06
    Imagine
    0.06
    ;'↵
    0.05
     дальней
    0.05
    Act Density 0.007%

    No Known Activations