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

    Neuronpedia

    INDEX
    Explanations

    we then verb

    np_acts-logits-general · gemini-2.5-flash-lite

    we will or can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    1.60
    3
    1.17
    ↵
    1.13
    te
    1.03
    án
    0.95
    i
    0.95
    um
    0.94
    ?
    0.88
    that
    0.88
    u
    0.86
    POSITIVE LOGITS
    nél
    1.21
    리
    1.16
     we
    0.94
    (
    0.94
    nione
    0.92
    =\
    0.89
    nika
    0.88
    0.88
    ಗಳ
    0.88
    ీ
    0.86
    Act Density 0.358%

    No Known Activations