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

    Neuronpedia

    INDEX
    Explanations

    acknowledgement phrases beginning with that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这里
    0.49
    这里的
    0.44
    راض
    0.43
    Removed
    0.39
    此处
    0.39
    Aqui
    0.39
    Here
    0.39
    𝑀
    0.39
    𝐷
    0.39
    包含
    0.38
    POSITIVE LOGITS
     reminds
    0.63
     sounds
    0.58
    ’
    0.55
     explains
    0.51
    sounds
    0.50
     Sounds
    0.49
     suena
    0.48
     seems
    0.47
     suono
    0.46
     settles
    0.45
    Act Density 0.008%

    No Known Activations