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

    Neuronpedia

    INDEX
    Explanations

    Abu Dhabi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    listView
    0.37
    Montgomery
    0.37
    pag
    0.36
    textView
    0.36
    cano
    0.36
     Ultimately
    0.35
     espada
    0.35
    Finally
    0.35
    aVal
    0.35
    urang
    0.35
    POSITIVE LOGITS
     Braz
    0.46
     Bras
    0.45
     وصحبه
    0.39
     Kel
    0.39
     Austrian
    0.38
    ўным
    0.38
     পয়েন্ট
    0.38
    黙
    0.38
     Kis
    0.37
    stris
    0.37
    Act Density 0.000%

    No Known Activations