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

    Neuronpedia

    INDEX
    Explanations

    repeat it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pretrained
    1.63
     массы
    1.56
     Kabupaten
    1.50
    kaan
    1.49
    рованное
    1.49
    uem
    1.49
     footnotes
    1.48
    gat
    1.47
    bem
    1.46
    ricted
    1.45
    POSITIVE LOGITS
    이어
    1.38
    з
    1.32
    ers
    1.30
    mathbb
    1.26
     Bxa
    1.23
     있는
    1.21
    Visa
    1.21
    1.17
    venues
    1.17
    quela
    1.16
    Act Density 0.000%

    No Known Activations