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

    Neuronpedia

    INDEX
    Explanations

    works or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     speeches
    0.47
     atteinte
    0.44
     хорошие
    0.43
     frü
    0.41
     వివా
    0.41
    写法
    0.40
     penggunaan
    0.39
     মুখের
    0.39
     argomento
    0.39
     disgu
    0.38
    POSITIVE LOGITS
     работают
    0.83
     trabalha
    0.74
     bekerja
    0.73
     Work
    0.72
     worked
    0.71
     trabajan
    0.71
     arbeitet
    0.71
    Work
    0.68
    ทำงาน
    0.68
     працю
    0.68
    Act Density 0.049%

    No Known Activations