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

    Neuronpedia

    INDEX
    Explanations

    closing, opening, sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    当我
    0.41
     catered
    0.38
    icklabels
    0.38
    混乱
    0.38
    ল্যান্ড
    0.38
    ürich
    0.37
    ২০০
    0.36
    ബരി
    0.36
    ढ़ा
    0.36
    moss
    0.36
    POSITIVE LOGITS
     સમય
    0.47
     ব্যাঙ্ক
    0.39
    OP
    0.38
     выбрать
    0.38
     OP
    0.37
     uncompromising
    0.36
    ગા
    0.36
    ibank
    0.36
    colorChoice
    0.35
     நேரம்
    0.35
    Act Density 0.000%

    No Known Activations