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

    Neuronpedia

    INDEX
    Explanations

    first or second

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     વધુ
    0.44
     नि
    0.43
     résultats
    0.42
     više
    0.42
     dalších
    0.42
     প্রসঙ্গ
    0.42
     wynik
    0.41
    풉
    0.41
     মহারাজ
    0.41
     Álvarez
    0.40
    POSITIVE LOGITS
     Think
    0.45
     kettle
    0.42
     example
    0.41
     first
    0.40
     due
    0.40
     so
    0.38
     working
    0.38
     Example
    0.38
     usually
    0.38
     stand
    0.38
    Act Density 0.000%

    No Known Activations