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

    Neuronpedia

    INDEX
    Explanations

    for the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crafting
    0.39
     цент
    0.37
     зі
    0.37
     atmospheric
    0.37
    .`
    0.36
     Lorena
    0.36
     Coin
    0.36
     Muscle
    0.36
     Forth
    0.35
     Centro
    0.35
    POSITIVE LOGITS
     umur
    0.43
    算是
    0.41
     약간
    0.41
     बताये
    0.40
    ման
    0.40
     خریداری
    0.40
    OB
    0.38
     लिखा
    0.38
     핵
    0.38
    ອກ
    0.38
    Act Density 0.000%

    No Known Activations