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

    Neuronpedia

    INDEX
    Explanations

    things other than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ខ្ល
    0.40
    arıyla
    0.39
    也很
    0.39
    ্নার
    0.39
    穷
    0.39
    াদুর
    0.39
     trophic
    0.38
    eará
    0.37
     சில
    0.37
    countplot
    0.36
    POSITIVE LOGITS
    以外の
    1.39
     non
    1.27
     beyond
    1.16
    非
    1.14
    以外
    1.12
     outside
    1.09
     selain
    1.05
     غير
    1.05
     außerhalb
    1.02
     other
    1.02
    Act Density 0.161%

    No Known Activations