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

    Neuronpedia

    INDEX
    Explanations

    line running

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Engineering
    0.48
    ARGET
    0.48
     gardens
    0.45
    ęs
    0.44
    rezz
    0.44
    Engineer
    0.43
    ğini
    0.43
     грамо
    0.43
     শ্রীযুক্ত
    0.43
     개의
    0.42
    POSITIVE LOGITS
    إ
    0.45
    itesse
    0.44
    2
    0.44
    羽
    0.44
    ز
    0.43
    zoic
    0.43
     एज
    0.42
    ा
    0.42
     one
    0.41
     to
    0.41
    Act Density 0.002%

    No Known Activations