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

    Neuronpedia

    INDEX
    Explanations

    Ariane, match, interpreters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䬲
    0.52
     instalaciones
    0.50
     wesentlich
    0.49
    جة
    0.48
    δο
    0.47
    অর্থাৎ
    0.47
    तुम्हारा
    0.46
    ᱫ
    0.45
     aktuellen
    0.45
    હીં
    0.44
    POSITIVE LOGITS
    '
    0.49
     อ
    0.46
    ยังมี
    0.45
     رسید
    0.44
     writ
    0.43
    لیس
    0.42
     repe
    0.42
    countries
    0.42
     stuffed
    0.42
     E
    0.42
    Act Density 0.001%

    No Known Activations