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

    Neuronpedia

    INDEX
    Explanations

    https links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aire
    1.42
    ing
    1.34
    ae
    1.30
    aient
    1.29
    ة
    1.28
    eers
    1.23
    eper
    1.21
    erweise
    1.20
    aa
    1.19
    る
    1.19
    POSITIVE LOGITS
    Архівовано
    1.89
    !]
    1.60
    ?]
    1.48
    ⿷
    1.40
     ])
    1.23
    @]
    1.21
    િ
    1.20
    @@]
    1.16
    ++]
    1.15
    ,]
    1.15
    Act Density 0.123%

    No Known Activations