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

    Neuronpedia

    INDEX
    Explanations

    Nicotiana benthamiana research

    np_max-act · gemini-2.0-flash

    tokens that mark or occur inside the assistant's replies (the assistant speaker/response segments).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ประธาน
    -0.07
    אירוע
    -0.07
    '].'/
    -0.07
     אתה
    -0.07
    📸
    -0.07
     nob
    -0.06
    젰
    -0.06
     datings
    -0.06
    🎏
    -0.06
     booklet
    -0.06
    POSITIVE LOGITS
     ск
    0.07
     delays
    0.07
    (tf
    0.07
    -sm
    0.07
    一个问题
    0.06
     ш
    0.06
    您好
    0.06
    섄
    0.06
    アン
    0.06
    OUNTER
    0.06
    Act Density 0.228%

    No Known Activations