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

    Neuronpedia

    INDEX
    Explanations

    time periods and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.59
    ри
    0.51
    an
    0.47
     will
    0.44
    و
    0.44
    og
    0.43
    ed
    0.43
    et
    0.42
    )。
    0.41
    el
    0.40
    POSITIVE LOGITS
    (
    0.44
    .
    0.41
    I
    0.38
    ৫
    0.37
    $:
    0.35
    ().
    0.35
    Му
    0.33
    Работа
    0.33
    #
    0.32
    .(
    0.32
    Act Density 0.228%

    No Known Activations