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

    Neuronpedia

    INDEX
    Explanations

    you can see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    খাস্ত
    0.44
    ONENTS
    0.43
    యోజ
    0.42
    ّة
    0.39
     promoting
    0.38
    ύν
    0.38
    ニュース
    0.38
     bertujuan
    0.38
    endix
    0.38
     وط
    0.38
    POSITIVE LOGITS
     tabella
    0.42
    誤差
    0.42
     Roboto
    0.41
     clearly
    0.40
     ifstream
    0.40
    Dirac
    0.40
     Exerc
    0.40
     による
    0.40
     grep
    0.40
     altar
    0.40
    Act Density 0.000%

    No Known Activations