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

    Neuronpedia

    INDEX
    Explanations

    pronounce, capped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uta
    0.45
     Daerah
    0.44
    tidak
    0.44
    University
    0.43
    ilo
    0.43
    away
    0.43
    awards
    0.43
    iveness
    0.42
     сада
    0.42
    art
    0.41
    POSITIVE LOGITS
     OBJECTTYPE
    0.50
    胍
    0.49
    Ꮏ
    0.48
     parmes
    0.44
    ⒏
    0.44
    轂
    0.44
     stirred
    0.41
    栞
    0.41
     zipped
    0.41
     cmdlet
    0.41
    Act Density 0.001%

    No Known Activations