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

    Neuronpedia

    INDEX
    Explanations

    personal information and constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    母
    0.50
    ко
    0.50
    占用
    0.47
    م
    0.46
    مه
    0.46
    лъ
    0.46
    ስታ
    0.45
     employs
    0.45
    وني
    0.44
    وق
    0.42
    POSITIVE LOGITS
     шка
    0.51
     vudd
    0.48
     Chiến
    0.47
     possano
    0.46
     steril
    0.46
     乾燥
    0.46
     пациен
    0.45
     na
    0.44
     fle
    0.43
     процентов
    0.43
    Act Density 0.009%

    No Known Activations