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

    Neuronpedia

    INDEX
    Explanations

    database filtering conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hôtels
    0.57
    Luong
    0.55
     sequência
    0.53
     رؤ
    0.53
     Friedman
    0.52
     మైసూరు
    0.52
    ฬ
    0.52
     portfolios
    0.52
     Federer
    0.52
    Despatx
    0.51
    POSITIVE LOGITS
    V
    0.68
    W
    0.66
    L
    0.66
     двадцать
    0.59
    "
    0.59
    IN
    0.57
    N
    0.57
    T
    0.56
    </h3>
    0.55
    до
    0.55
    Act Density 0.000%

    No Known Activations