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

    Neuronpedia

    INDEX
    Explanations

    I know that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     `=
    0.51
     Без
    0.46
    éter
    0.45
    徬
    0.44
    Без
    0.43
    phal
    0.41
    ैट
    0.40
     rád
    0.40
    بير
    0.39
    如下图
    0.39
    POSITIVE LOGITS
     either
    0.45
     Either
    0.42
    消费
    0.41
     terr
    0.39
     drain
    0.37
    인다
    0.37
     thổ
    0.37
     rov
    0.37
    🕍
    0.36
     immediate
    0.36
    Act Density 0.001%

    No Known Activations