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

    Neuronpedia

    INDEX
    Explanations

    ever since

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     massima
    1.30
     massimo
    1.25
    𝖔
    1.24
    MAT
    1.19
     использу
    1.16
    Nella
    1.15
    兗
    1.15
     atteinte
    1.14
    N
    1.13
     машиналары
    1.13
    POSITIVE LOGITS
    m
    1.38
    varande
    1.33
    t
    1.33
    r
    1.32
    en
    1.30
    d
    1.27
    g
    1.17
    ne
    1.16
    piration
    1.14
    ı
    1.13
    Act Density 0.003%

    No Known Activations