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

    Neuronpedia

    INDEX
    Explanations

    tailor to specific needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.29
    т
    1.25
    t
    1.20
    ла
    1.11
     is
    1.07
    ด
    1.06
    па
    0.94
     and
    0.89
     manera
    0.87
    ен
    0.86
    POSITIVE LOGITS
    one
    1.09
    K
    1.01
    E
    0.91
    phins
    0.91
    ade
    0.90
    od
    0.89
    ir
    0.88
    Tail
    0.87
    ：
    0.84
    itin
    0.82
    Act Density 0.009%

    No Known Activations