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

    Neuronpedia

    INDEX
    Explanations

    names following titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cesz
    0.33
    Tienes
    0.31
    ૯
    0.31
    வற்றை
    0.29
    怎样
    0.28
     કેવી
    0.28
    ༩
    0.28
    Therefore
    0.28
    worldly
    0.27
    ೯
    0.27
    POSITIVE LOGITS
     U
    0.31
     T
    0.31
    S
    0.31
    O
    0.31
     N
    0.30
     bowel
    0.30
    A
    0.30
    T
    0.29
     O
    0.29
     sales
    0.29
    Act Density 0.061%

    No Known Activations