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

    Neuronpedia

    INDEX
    Explanations

    SQL, numbers, and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    licts
    0.41
    ್ಧ
    0.40
    文本
    0.38
     캐릭터
    0.37
     Characters
    0.36
     maxLength
    0.36
     UTF
    0.36
    ográficas
    0.36
     hạn
    0.36
     หนังสือ
    0.35
    POSITIVE LOGITS
    ቤት
    0.45
    Small
    0.41
    協会
    0.41
     eleven
    0.41
     десять
    0.40
    airbnb
    0.38
     pri
    0.38
    Pri
    0.38
     ten
    0.38
    (`#
    0.38
    Act Density 0.003%

    No Known Activations