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

    Neuronpedia

    INDEX
    Explanations

    DOIs and article links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒋾
    0.44
    沇
    0.44
     தாவர
    0.41
    신도시
    0.40
    退休
    0.39
    älfte
    0.39
    淝
    0.39
    ጋገብ
    0.38
    gramModel
    0.38
     impulso
    0.38
    POSITIVE LOGITS
    d
    0.44
    /
    0.44
    j
    0.43
    im
    0.42
    p
    0.42
    l
    0.41
    lag
    0.40
    i
    0.40
    ne
    0.39
    z
    0.39
    Act Density 0.001%

    No Known Activations