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

    Neuronpedia

    INDEX
    Explanations

    `anon` and `printed`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    party
    0.39
    忙
    0.39
    middlewares
    0.38
     outfitted
    0.37
    assemble
    0.37
    cleaning
    0.37
    ing
    0.37
    𝘮
    0.36
     المبار
    0.36
     entrusted
    0.36
    POSITIVE LOGITS
     dưới
    0.36
    Quotes
    0.36
     obie
    0.36
     composite
    0.35
    Equivalent
    0.35
    两者
    0.34
    पणे
    0.34
    ]#
    0.34
    ριθ
    0.34
     nếu
    0.33
    Act Density 0.000%

    No Known Activations