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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.33
    0.28
    1
    0.26
    -
    0.25
    A
    0.24
     (
    0.24
    S
    0.24
    E
    0.24
     and
    0.24
     A
    0.23
    POSITIVE LOGITS
    akkhati
    0.23
     بالټ
    0.22
     Tjiwarl
    0.22
    <unused497>
    0.22
    繁忙時間
    0.22
     bungal
    0.22
    <unused481>
    0.22
    คาเดมี
    0.22
    preliquidacion
    0.21
    蟎
    0.21
    Act Density 0.200%

    No Known Activations