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

    Neuronpedia

    INDEX
    Explanations

    only respond in JSON

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ちょっと
    0.42
     \,
    0.39
    やっぱり
    0.37
     সত্যিই
    0.36
    pretty
    0.34
     সম্ভবত
    0.34
     trochę
    0.34
     やっぱり
    0.33
    clearRect
    0.33
    
    0.33
    POSITIVE LOGITS
     antwort
    0.47
     paraphr
    0.46
     henceforth
    0.45
     paraphrase
    0.45
    のみ
    0.44
     ONLY
    0.44
     वाक्य
    0.43
     sentences
    0.43
     மட்டுமே
    0.43
    不超过
    0.42
    Act Density 0.525%

    No Known Activations