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

    Neuronpedia

    INDEX
    Explanations

    faster than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    triple
    0.41
    </h2>
    0.38
    time
    0.38
    Triple
    0.36
    圈
    0.36
    Big
    0.36
     নিশ্চিত
    0.36
     હાઉસ
    0.35
    Bought
    0.35
     అంటే
    0.34
    POSITIVE LOGITS
     tanpa
    0.44
     unsupported
    0.42
    ቓ
    0.42
     recomenda
    0.42
     Bahasa
    0.41
     jezik
    0.41
     bás
    0.41
     usuários
    0.41
    EnglishMarks
    0.40
    não
    0.39
    Act Density 0.000%

    No Known Activations