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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash

    This neuron detects “warning” or “experimental” notices and disclaimers indicating that an API or feature is unstable or subject to change.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    рач
    -0.07
    :');↵
    -0.06
     practically
    -0.06
    _ud
    -0.06
    фф
    -0.06
     civil
    -0.06
     charity
    -0.06
    (pts
    -0.06
     propriet
    -0.06
    ertas
    -0.06
    POSITIVE LOGITS
     Naomi
    0.07
     sala
    0.07
     Sag
    0.06
     geniş
    0.06
    .radio
    0.06
     přem
    0.06
    _DIPSETTING
    0.06
    	fd
    0.06
    WindowTitle
    0.06
     Potion
    0.06
    Act Density 0.007%

    No Known Activations