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

    Neuronpedia

    INDEX
    Explanations

    various concepts within categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UM
    0.44
    uks
    0.43
    over
    0.40
     resulting
    0.39
    pt
    0.38
     distortions
    0.38
    uk
    0.38
    ın
    0.38
    parts
    0.38
    nil
    0.38
    POSITIVE LOGITS
    ქვს
    0.42
    ၶ
    0.41
     procured
    0.40
     Breg
    0.40
     Cousins
    0.40
     puedan
    0.39
     yaşında
    0.39
    луйста
    0.38
    squre
    0.38
     уровне
    0.38
    Act Density 0.000%

    No Known Activations