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

    Neuronpedia

    INDEX
    Explanations

    codes and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     You
    0.55
     Mei
    0.54
     is
    0.54
     Before
    0.52
     WITH
    0.50
     Ji
    0.50
     If
    0.49
     Za
    0.48
     Without
    0.48
     By
    0.47
    POSITIVE LOGITS
    Пре
    0.60
    ст
    0.57
    9
    0.57
    ست
    0.56
    т
    0.55
    ЕН
    0.52
    して
    0.51
    ста
    0.50
    Фото
    0.50
    7
    0.50
    Act Density 0.099%

    No Known Activations