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

    Neuronpedia

    INDEX
    Explanations

    clothing, objects, and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eg
    0.36
     ub
    0.36
     구성
    0.36
     oluştur
    0.33
     පේශ
    0.33
     våra
    0.32
    <0x0E>
    0.32
     Ew
    0.32
     cenderung
    0.32
    颦
    0.32
    POSITIVE LOGITS
    лган
    0.34
    ボー
    0.33
     cheerful
    0.30
    யில்
    0.29
     hotel
    0.29
    мент
    0.29
    long
    0.29
    ባት
    0.29
     convent
    0.29
    েলের
    0.29
    Act Density 0.003%

    No Known Activations