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

    Neuronpedia

    INDEX
    Explanations

    configuration, you think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ድግዳ
    0.41
    ዠ
    0.40
    that
    0.39
    ግዳ
    0.39
    frast
    0.37
    हालांकि
    0.37
    ômios
    0.36
    ız
    0.36
    și
    0.36
    তিতে
    0.35
    POSITIVE LOGITS
    ↵
    0.72
    ER
    0.60
     THE
    0.52
    ERS
    0.50
    :
    0.49
    ZIONE
    0.48
     ONLY
    0.48
    ORY
    0.47
    ATING
    0.46
    ﺍ
    0.45
    Act Density 0.093%

    No Known Activations