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

    Neuronpedia

    INDEX
    Explanations

    Solution Explorer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    1.10
    上
    1.01
     is
    0.99
     to
    0.96
    สำหรับ
    0.91
    ット
    0.90
    ના
    0.88
    真人
    0.88
    很
    0.84
    ू
    0.82
    POSITIVE LOGITS
    us
    1.05
    ле
    1.02
    ar
    0.93
    ၀
    0.93
    li
    0.92
    an
    0.89
    ad
    0.89
    il
    0.89
    ir
    0.88
    ۰
    0.88
    Act Density 0.000%

    No Known Activations