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

    Neuronpedia

    INDEX
    Explanations

    identifying bugs, defects, or security issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uten
    0.45
     நிறுவன
    0.43
     XXL
    0.43
     Zusammen
    0.43
    SampleSize
    0.43
     Excluding
    0.42
     pekerjaan
    0.42
     WITHOUT
    0.41
    setWidth
    0.41
     measurements
    0.41
    POSITIVE LOGITS
    thread
    0.42
     thread
    0.39
    every
    0.39
    ard
    0.38
    announced
    0.38
     preview
    0.38
    discover
    0.38
    oto
    0.38
    roy
    0.38
    mon
    0.38
    Act Density 0.001%

    No Known Activations