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

    Neuronpedia

    INDEX
    Explanations

    link layer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perimeter
    0.46
     .
    0.46
     streetlight
    0.46
     epiphany
    0.46
     are
    0.45
     lithium
    0.44
     grasp
    0.44
    는
    0.44
     gasoline
    0.43
     propane
    0.43
    POSITIVE LOGITS
    ους
    0.68
    𝚙
    0.64
     ل
    0.64
    щото
    0.63
    periods
    0.62
    𝚅
    0.62
    𝗎
    0.61
    𝚏
    0.61
    𝙳
    0.60
    čnom
    0.59
    Act Density 0.120%

    No Known Activations