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

    Neuronpedia

    INDEX
    Explanations

    attention Matrix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     управления
    0.45
    ilot
    0.45
    countries
    0.44
     İl
    0.44
    ounds
    0.43
    fichier
    0.43
    diameter
    0.42
    dilation
    0.42
    pletion
    0.42
    necklace
    0.41
    POSITIVE LOGITS
    妥
    0.46
     tentativas
    0.46
    OFF
    0.45
     informazioni
    0.43
    ወቅ
    0.43
     viewBox
    0.42
     stoves
    0.42
     Provisions
    0.42
     informasjon
    0.42
    TA
    0.41
    Act Density 0.000%

    No Known Activations