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

    Neuronpedia

    INDEX
    Explanations

    age, you, signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.55
    m
    0.52
     alors
    0.49
    ÉS
    0.48
    м
    0.47
    नैतिक
    0.46
    Marco
    0.45
     Ét
    0.45
    gevens
    0.45
    াকারী
    0.45
    POSITIVE LOGITS
     كما
    0.45
     كلها
    0.44
     disco
    0.44
     preparar
    0.42
     طبي
    0.41
     diferenci
    0.41
     поя
    0.41
     لب
    0.41
    షల్
    0.40
     方向
    0.40
    Act Density 0.000%

    No Known Activations