INDEX
    Explanations

    plants, agriculture, and nature

    New Auto-Interp
    Negative Logits
    ست
    0.54
    ול
    0.54
     Zeichen
    0.54
    करण
    0.54
     कुलकर्णी
    0.53
     Ángeles
    0.52
    También
    0.51
     संवाददाता
    0.51
     lông
    0.51
     zaključ
    0.51
    POSITIVE LOGITS
     shrubs
    0.75
    forest
    0.65
     mangroves
    0.65
    0.63
    ли
    0.63
     seedlings
    0.62
     orchards
    0.61
    🌿
    0.61
    veget
    0.61
    leaves
    0.60
    Act Density 1.397%

    No Known Activations