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

    Neuronpedia

    INDEX
    Explanations

    into real-life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NumericVector
    0.43
     ©
    0.40
     Bats
    0.40
     |”
    0.40
    ).
    0.39
     _
    0.39
     tweepy
    0.39
     gus
    0.39
     RNN
    0.38
     regist
    0.38
    POSITIVE LOGITS
     ފ
    0.49
    সাহিত
    0.49
     หมด
    0.47
    ಎಸ್
    0.46
     vroeg
    0.46
    까지
    0.46
     脱
    0.46
    퓨
    0.45
     সংগ্রামী
    0.45
    igual
    0.45
    Act Density 0.000%

    No Known Activations