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

    Neuronpedia

    INDEX
    Explanations

    the World Cup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    many
    0.59
    al
    0.54
    mano
    0.54
    ant
    0.54
    ne
    0.53
    na
    0.53
    inan
    0.53
    ich
    0.51
    ات
    0.51
     Бан
    0.51
    POSITIVE LOGITS
     World
    0.53
    と一緒に
    0.50
    \
    0.48
     achievement
    0.46
     insignificant
    0.45
     build
    0.45
    အတွင်း
    0.44
     SW
    0.44
     Secretary
    0.43
    <0x80>
    0.43
    Act Density 0.001%

    No Known Activations