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

    Neuronpedia

    INDEX
    Explanations

    non-standard characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵↵
    0.70
    ↵↵↵↵
    0.60
    ↵↵↵↵↵
    0.60
     read
    0.59
     ist
    0.59
     `
    0.59
     description
    0.59
     is
    0.58
     informazioni
    0.56
     ",
    0.54
    POSITIVE LOGITS
    ಭಾವ
    0.64
    ходов
    0.63
    ঽ
    0.63
     तीव्रता
    0.62
    efeuille
    0.61
    squre
    0.61
    PointCloud
    0.61
    ໜ
    0.61
    heben
    0.60
    centers
    0.60
    Act Density 0.085%

    No Known Activations