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

    Neuronpedia

    INDEX
    Explanations

    leader, journal, lead, released

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     üst
    1.37
    ్ర
    1.30
    摩擦
    1.28
     ғ
    1.25
    rahm
    1.25
    Ply
    1.23
     foiled
    1.21
     Kool
    1.20
     affix
    1.18
    exual
    1.18
    POSITIVE LOGITS
    a
    1.83
    一个
    1.42
    ০
    1.34
    aq
    1.30
    া
    1.21
    aile
    1.21
    아
    1.21
    kund
    1.20
    eux
    1.17
    ا
    1.17
    Act Density 0.000%

    No Known Activations