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

    Neuronpedia

    INDEX
    Explanations

    parenthesized math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝟏
    0.31
     прось
    0.30
     కోసం
    0.29
     ثلاثة
    0.29
     إلى
    0.29
     માટે
    0.29
     الصنا
    0.29
    ،
    0.29
    的作用
    0.28
    的技术
    0.28
    POSITIVE LOGITS
     the
    0.41
    the
    0.32
     your
    0.30
     n
    0.29
     our
    0.29
    w
    0.29
     f
    0.28
     itinerant
    0.28
     N
    0.28
    new
    0.28
    Act Density 0.158%

    No Known Activations