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

    Neuronpedia

    INDEX
    Explanations

    German, meeting, color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.53
     predomin
    0.49
    0.47
     Larger
    0.43
             
    0.43
                  
    0.42
     Large
    0.42
     both
    0.41
     B
    0.41
     seems
    0.41
    POSITIVE LOGITS
     whatsapp
    0.52
    Pokud
    0.50
     మరియు
    0.48
     lmao
    0.48
    Você
    0.47
     malaysia
    0.47
     ቫ
    0.47
    hamdulillah
    0.46
    Anyways
    0.46
    Ს
    0.46
    Act Density 0.028%

    No Known Activations