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

    Neuronpedia

    INDEX
    Explanations

    state changes or deterioration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.38
    1
    0.38
    -
    0.35
    ود
    0.31
    ِ
    0.31
    0.30
    2
    0.29
    8
    0.27
    ту
    0.27
    করে
    0.26
    POSITIVE LOGITS
     wodurch
    0.44
     oleh
    0.40
     bởi
    0.40
     más
    0.39
     ফলে
    0.38
     ហើយ
    0.37
     vollständig
    0.37
     สาว
    0.37
     ninguém
    0.37
     andRow
    0.37
    Act Density 0.058%

    No Known Activations