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

    Neuronpedia

    INDEX
    Explanations

    slightly less common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ทรวง
    0.46
     tanaman
    0.45
     Thirdly
    0.44
     seorang
    0.43
    rdquo
    0.43
    amme
    0.43
    köz
    0.42
     prerog
    0.42
     blooms
    0.42
     şart
    0.42
    POSITIVE LOGITS
     elsewhere
    0.50
    超
    0.46
     અન્ય
    0.46
    或其他
    0.46
    U
    0.46
     अन्य
    0.46
    y
    0.45
    送
    0.44
    E
    0.44
    通信
    0.44
    Act Density 0.003%

    No Known Activations