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

    Neuronpedia

    INDEX
    Explanations

    fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    1.27
    '
    1.27
    it
    1.19
    ’
    1.07
    ası
    1.06
    iton
    1.05
    on
    1.03
    zyć
    1.01
    edes
    1.00
    ani
    0.99
    POSITIVE LOGITS
    О
    1.03
     pă
    0.95
    }$.
    0.94
     bairro
    0.92
    У
    0.91
    Пре
    0.89
     quell
    0.89
     weekends
    0.88
     ውሃ
    0.88
    ОР
    0.88
    Act Density 0.001%

    No Known Activations