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

    Neuronpedia

    INDEX
    Explanations

    issues based

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தேர்த
    0.48
     койма
    0.41
    èng
    0.41
     installers
    0.41
     निर्देशक
    0.41
    ষ্কার
    0.40
    怂
    0.38
    រ
    0.38
     हालांकि
    0.37
     نیرو
    0.37
    POSITIVE LOGITS
     Radius
    0.41
     placenta
    0.40
     Readable
    0.40
     Reef
    0.39
    取る
    0.39
     HeLa
    0.38
     Obit
    0.38
     Emil
    0.38
     Sankt
    0.38
     diatomic
    0.38
    Act Density 0.000%

    No Known Activations