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

    Neuronpedia

    INDEX
    Explanations

    commonsense and creative commons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    2.61
    ight
    2.51
    estomac
    2.50
    tschaft
    2.49
    ான
    2.46
     attent
    2.45
    arie
    2.43
    и
    2.41
     deter
    2.39
    과
    2.37
    POSITIVE LOGITS
     macam
    2.89
     불구하고
    2.86
    𝖙
    2.69
    लिये
    2.62
    ை
    2.58
    ویت
    2.55
    ယာ
    2.50
    𝖔
    2.50
    которые
    2.50
     tecnológica
    2.48
    Act Density 0.023%

    No Known Activations