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

    Neuronpedia

    INDEX
    Explanations

    asking me about language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ord
    0.41
    Army
    0.41
     army
    0.41
    Stay
    0.40
     [](
    0.39
    刈
    0.39
     Army
    0.39
    aze
    0.39
    舜
    0.38
    軍
    0.38
    POSITIVE LOGITS
    alchemy
    0.38
    体会
    0.38
    ђа
    0.38
    āla
    0.37
     النسبيه
    0.37
     Tera
    0.37
    בום
    0.36
    IKO
    0.36
    showMessage
    0.36
     Yatha
    0.36
    Act Density 0.000%

    No Known Activations