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

    Neuronpedia

    INDEX
    Explanations

    data keys and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    طاء
    1.18
    夠
    1.15
    ۋ
    1.13
    用来
    1.12
    بتدي
    1.09
    ...\...\...\...\
    1.09
    缩
    1.07
    verages
    1.07
    從
    1.06
    يف
    1.06
    POSITIVE LOGITS
     these
    1.64
     this
    1.58
     it
    1.48
     यह
    1.48
     یہ
    1.44
    these
    1.44
     우리는
    1.40
     Newcastle
    1.39
     MAH
    1.37
     they
    1.36
    Act Density 0.131%

    No Known Activations