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

    Neuronpedia

    INDEX
    Explanations

    lists with numbers and bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mga
    2.09
    ви
    2.08
    αν
    2.03
     fillet
    2.00
    onaise
    1.98
    ęcie
    1.92
    и
    1.92
    ści
    1.88
    ul
    1.88
    Repost
    1.79
    POSITIVE LOGITS
    و
    3.13
    ה
    2.88
    ো
    1.96
    น้อง
    1.95
     baff
    1.91
    এক
    1.90
    ない
    1.88
    ק
    1.84
    ﺘ
    1.84
     Calm
    1.83
    Act Density 0.245%

    No Known Activations