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

    Neuronpedia

    INDEX
    Explanations

    head of, body of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ति
    0.74
    घव
    0.74
    ره
    0.72
    টু
    0.71
     Vielen
    0.71
    сных
    0.70
    干
    0.69
    Перед
    0.69
     trabal
    0.68
    хан
    0.67
    POSITIVE LOGITS
     mondiale
    0.80
    sodium
    0.77
     матч
    0.72
    arote
    0.70
    atemala
    0.69
    alphas
    0.69
     중국
    0.68
     maroc
    0.68
    arın
    0.67
     segno
    0.67
    Act Density 0.001%

    No Known Activations