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

    Neuronpedia

    INDEX
    Explanations

    petitions and tombs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Мен
    0.54
    Ш
    0.54
    Ж
    0.52
    ﮕ
    0.51
    Estas
    0.50
    К
    0.50
    について
    0.49
     cinq
    0.49
    Тех
    0.49
    х
    0.48
    POSITIVE LOGITS
    ravel
    0.49
    aa
    0.46
     A
    0.46
    ino
    0.44
     But
    0.44
    atu
    0.44
    il
    0.43
     temporally
    0.43
     但是
    0.43
     B
    0.42
    Act Density 0.030%

    No Known Activations