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

    Neuronpedia

    INDEX
    Explanations

    principles and policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    common
    0.40
    स्थ
    0.38
    なあ
    0.37
    mid
    0.37
    Vol
    0.37
    round
    0.37
    tum
    0.37
     nim
    0.36
     remon
    0.36
     unpublished
    0.35
    POSITIVE LOGITS
    ından
    0.42
    olicy
    0.42
     principles
    0.41
    zesz
    0.41
    ிற்
    0.40
     Principles
    0.40
     barring
    0.39
    ﻌ
    0.38
     Slovakia
    0.38
    ueve
    0.37
    Act Density 0.000%

    No Known Activations