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

    Neuronpedia

    INDEX
    Explanations

    questions ending with 'to?'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    M
    1.48
    ী
    1.46
    A
    1.39
    rafo
    1.35
    llä
    1.34
    C
    1.34
    Waar
    1.28
    puede
    1.25
    d
    1.25
    or
    1.23
    POSITIVE LOGITS
    .
    2.08
    。
    1.88
     that
    1.80
    ,
    1.66
    ，
    1.59
     for
    1.52
    ?
    1.52
     on
    1.50
     (
    1.49
    !
    1.41
    Act Density 10.279%

    No Known Activations