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

    Neuronpedia

    INDEX
    Explanations

    communicating with Bottom Shelf owners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Notwithstanding
    0.48
     supremum
    0.48
     exodus
    0.45
     specular
    0.45
     mancanza
    0.45
     epitome
    0.44
    উপ
    0.43
     mengambil
    0.43
     ambulatory
    0.42
     hypoallergenic
    0.42
    POSITIVE LOGITS
    ener
    0.43
    ovia
    0.39
    ocus
    0.38
    rep
    0.38
    æ
    0.38
    )
    0.38
    ore
    0.37
    ett
    0.37
    ė
    0.37
    í
    0.36
    Act Density 0.008%

    No Known Activations