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

    Neuronpedia

    INDEX
    Explanations

    question starters like because, who, porque

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -2.63
     чем
    -2.11
     favoritas
    -2.11
    躂
    -2.09
     But
    -2.09
    ཫ
    -2.09
    焢
    -2.08
    擼
    -2.05
    เพราะ
    -2.02
    と言われる
    -1.98
    POSITIVE LOGITS
    0
    2.41
    {
    2.16
     to
    2.09
    $
    2.00
    You
    1.99
    的人物
    1.94
    ”
    1.93
     buses
    1.90
    ;
    1.89
    遴
    1.88
    Act Density 0.000%

    No Known Activations