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

    Neuronpedia

    INDEX
    Explanations

    just plain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     just
    2.20
     Just
    2.06
    Just
    2.02
     только
    1.82
     hanya
    1.81
    just
    1.80
     JUST
    1.75
     only
    1.64
     justru
    1.63
     Only
    1.61
    POSITIVE LOGITS
    ifiably
    2.43
     plain
    1.53
    ification
    1.31
    ifications
    1.29
    ified
    1.28
    ifying
    1.26
    ifiable
    1.20
     Plain
    1.17
    ifies
    1.16
    ify
    1.11
    Act Density 0.164%

    No Known Activations