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

    Neuronpedia

    INDEX
    Explanations

    compliance and summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     governance
    0.41
     Studying
    0.40
     ভয়
    0.39
     traditional
    0.36
     analysing
    0.36
     मालिक
    0.36
    listar
    0.36
     mediocre
    0.35
    मर्श
    0.35
     depress
    0.35
    POSITIVE LOGITS
     인한
    0.45
     объ
    0.44
     souvenirs
    0.40
    کنندگان
    0.39
    થી
    0.39
    用水
    0.38
    čené
    0.38
    ə
    0.38
    抄
    0.38
    ﮔ
    0.38
    Act Density 0.000%

    No Known Activations