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

    Neuronpedia

    INDEX
    Explanations

    galley web, Netter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {//
    0.54
    {
    0.52
     adsorbent
    0.49
     televis
    0.48
     is
    0.48
    িকপ্ট
    0.47
    綿
    0.47
     ponad
    0.46
     Telefon
    0.45
     komplet
    0.45
    POSITIVE LOGITS
    ור
    0.55
    and
    0.52
    то
    0.51
    от
    0.50
    é
    0.49
    ı
    0.49
    iances
    0.48
    re
    0.47
    er
    0.47
    на
    0.47
    Act Density 0.000%

    No Known Activations