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

    Neuronpedia

    INDEX
    Explanations

    of course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ığını
    0.73
     If
    0.72
     and
    0.71
    And
    0.69
    If
    0.65
     tweaks
    0.65
     And
    0.64
    ian
    0.61
     alterations
    0.61
     eğer
    0.61
    POSITIVE LOGITS
     Tenemos
    0.79
     Comenz
    0.77
    tableau
    0.77
    ться
    0.75
     Tìm
    0.75
     Recher
    0.74
     Показа
    0.74
     Цвет
    0.74
    r
    0.74
    sport
    0.73
    Act Density 0.001%

    No Known Activations