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

    Neuronpedia

    INDEX
    Explanations

    equation components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     those
    0.91
    those
    0.88
    Those
    0.86
     Those
    0.86
     thofe
    0.69
     thoſe
    0.69
    那种
    0.68
     той
    0.67
     aquella
    0.67
     تلك
    0.67
    POSITIVE LOGITS
     =
    5.01
    =
    4.00
     $=
    3.70
     $=$
    3.35
    ＝
    3.30
    $=
    3.20
     =,
    3.14
     ="
    3.13
     $=\
    3.12
     =\
    3.01
    Act Density 1.000%

    No Known Activations