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

    Neuronpedia

    INDEX
    Explanations

    numbers/codes/structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一
    0.42
     in
    0.40
    會
    0.38
     an
    0.34
    在
    0.34
    of
    0.33
     one
    0.33
    IT
    0.33
     be
    0.32
    过
    0.31
    POSITIVE LOGITS
    is
    0.45
    -
    0.42
    ない
    0.38
    ນິກ
    0.38
    nG
    0.38
    ຜະລິດຕະພັນ
    0.37
    lerine
    0.36
    ເລັກ
    0.36
     resultados
    0.36
     composants
    0.36
    Act Density 1.459%

    No Known Activations