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

    Neuronpedia

    INDEX
    Explanations

    AI vs human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জারি
    0.37
    ടൊപ്പം
    0.37
    ର୍
    0.36
     गेंदबाजों
    0.35
     покрытия
    0.33
    Functional
    0.33
     전국
    0.33
    macht
    0.32
    ောက်ပ
    0.32
    oller
    0.32
    POSITIVE LOGITS
     humans
    3.36
     human
    3.33
     челове
    3.00
    人类
    3.00
     Humans
    2.97
     인간
    2.97
     humanos
    2.94
    humans
    2.92
    Humans
    2.89
    human
    2.88
    Act Density 0.094%

    No Known Activations