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

    Neuronpedia

    INDEX
    Explanations

    existential dread, waiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Palais
    0.46
    人物
    0.45
     মহাপ
    0.44
     mappa
    0.42
     osoby
    0.42
    ᕆ
    0.41
    ປະກອບ
    0.41
     Tribute
    0.41
     popolo
    0.40
    سری
    0.40
    POSITIVE LOGITS
     दोन
    0.41
     જ
    0.37
     -,
    0.36
     ૧
    0.36
    த்திய
    0.35
    designed
    0.34
     இரண்டு
    0.34
    ('|
    0.34
     दो
    0.33
    ंदी
    0.33
    Act Density 0.001%

    No Known Activations