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

    Neuronpedia

    INDEX
    Explanations

    numbers like 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idéal
    0.51
     diejenigen
    0.50
    {~
    0.50
    oooo
    0.49
     Dazu
    0.49
    ۰۰
    0.49
    ────────
    0.48
    𝐬
    0.48
     ideales
    0.48
    ORE
    0.48
    POSITIVE LOGITS
    на
    0.73
    ет
    0.60
    <0xBC>
    0.59
    ного
    0.59
    ন
    0.58
    ু
    0.58
    ور
    0.58
    ay
    0.57
    ı
    0.56
    ariş
    0.55
    Act Density 3.460%

    No Known Activations