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

    Neuronpedia

    INDEX
    Explanations

    else followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    1.92
    .
    1.64
    ade
    1.57
    ing
    1.52
    er
    1.51
    i
    1.50
    '
    1.45
    ?
    1.45
    !
    1.39
    {
    1.38
    POSITIVE LOGITS
    на
    1.41
     centrally
    1.26
    ர
    1.20
    ш
    1.20
     самое
    1.19
    ರ್
    1.17
    يا
    1.16
    দের
    1.13
    ુ
    1.10
     перший
    1.09
    Act Density 0.013%

    No Known Activations