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

    Neuronpedia

    INDEX
    Explanations

    Thai and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֠
    -1.27
     for
    -1.20
     naast
    -1.09
     says
    -1.05
     tijdens
    -1.03
     equipe
    -1.01
     waarmee
    -1.01
    髂
    -1.00
     ensi
    -1.00
     only
    -1.00
    POSITIVE LOGITS
     harten
    1.45
     frucht
    1.37
    ORAGE
    1.20
     miroir
    1.20
     irmãos
    1.19
     čás
    1.16
    鸰
    1.16
    玊
    1.16
    ſſen
    1.16
     ранее
    1.14
    Act Density 0.001%

    No Known Activations