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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act · gemini-2.0-flash

    This neuron detects the “H” in the “HN” of Ask HN–style post headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     aka
    -0.07
    ुमत
    -0.07
     LCD
    -0.07
     fds
    -0.06
    ERM
    -0.06
    phem
    -0.06
    	In
    -0.06
    สถ
    -0.06
    spd
    -0.06
     Gem
    -0.06
    POSITIVE LOGITS
    .minLength
    0.07
     nons
    0.07
    (',
    0.06
     itertools
    0.06
    []{"
    0.06
    иной
    0.06
    _THEME
    0.06
    .basic
    0.06
    ','
    0.06
     encryption
    0.06
    Act Density 0.016%

    No Known Activations