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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a high level of reliability or established knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    well known, well established

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.65
     utafitiHapana
    -0.64
    पया
    -0.57
    orsese
    -0.54
    CloseOperation
    -0.54
    istoitu
    -0.52
     arşivlendi
    -0.50
     незавершена
    -0.50
     Chwiliwch
    -0.47
    Попис
    -0.47
    POSITIVE LOGITS
     well
    0.93
     хорошо
    0.80
     dobrze
    0.78
     jól
    0.71
    well
    0.66
     dobře
    0.65
     perfectly
    0.63
     добре
    0.62
     gerai
    0.60
    Well
    0.60
    Act Density 0.032%

    No Known Activations