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

    Neuronpedia

    INDEX
    Explanations

    common phrases and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ec
    0.48
    echo
    0.48
    link
    0.48
     sie
    0.46
    ece
    0.46
    laden
    0.46
     وهذا
    0.46
    sniffer
    0.45
    itet
    0.45
    സൈ
    0.45
    POSITIVE LOGITS
     prank
    0.51
     праців
    0.44
    转变
    0.43
    یدم
    0.42
     rearranging
    0.42
    ные
    0.42
     използ
    0.41
    ний
    0.40
     दोस्त
    0.40
     giocatore
    0.40
    Act Density 0.002%

    No Known Activations