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

    Neuronpedia

    INDEX
    Explanations

    Trevor Project, Trans Lifeline, RAINN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রে
    0.43
     प्रे
    0.41
     pthread
    0.40
     thread
    0.38
     بذ
    0.38
     ಔ
    0.37
     ज्ञापन
    0.37
     obsessive
    0.37
    स्फोट
    0.36
     પ્રે
    0.36
    POSITIVE LOGITS
    VAL
    0.35
    Witness
    0.35
     Gr
    0.34
     Valent
    0.34
    Val
    0.34
    Vo
    0.34
    cyber
    0.33
    witness
    0.33
    val
    0.32
    Tam
    0.32
    Act Density 0.011%

    No Known Activations