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

    Neuronpedia

    INDEX
    Explanations

    apostrophes and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ments
    0.51
    呕
    0.49
    т
    0.49
     abstracts
    0.49
    敒
    0.49
    ापुर
    0.48
    客观
    0.48
     islands
    0.48
    تس
    0.48
    ，“
    0.48
    POSITIVE LOGITS
    ati
    0.46
     STYLE
    0.44
     stylu
    0.43
     നമ്പർ
    0.42
     generasi
    0.41
    rian
    0.41
    à
    0.41
    IAN
    0.41
     belle
    0.41
     सेक्शन
    0.40
    Act Density 0.001%

    No Known Activations