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

    Neuronpedia

    INDEX
    Explanations

    AI capabilities explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     couplings
    0.45
     imasmim
    0.44
     suppose
    0.42
    RIN
    0.40
    QI
    0.39
    chym
    0.39
    启动
    0.38
     separator
    0.38
     fram
    0.38
    Brazil
    0.38
    POSITIVE LOGITS
    iket
    0.44
    maket
    0.42
    turning
    0.41
    حو
    0.40
     Tournament
    0.39
    ill
    0.39
     জিজ্ঞ
    0.38
    Tournament
    0.38
    lend
    0.38
    ال
    0.37
    Act Density 0.025%

    No Known Activations