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

    Neuronpedia

    INDEX
    Explanations

    find out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     выбора
    0.42
    ピング
    0.40
    غرافيا
    0.38
    ことから
    0.36
    وية
    0.35
    ويات
    0.35
     নিউজ
    0.35
    ارة
    0.35
    லிய
    0.35
    кту
    0.35
    POSITIVE LOGITS
     find
    0.58
     solace
    0.58
     out
    0.57
     suitable
    0.55
     inspiration
    0.55
     ways
    0.53
     fault
    0.50
     refuge
    0.50
     answers
    0.49
    find
    0.47
    Act Density 0.037%

    No Known Activations