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

    Neuronpedia

    INDEX
    Explanations

    locations and plagiarism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    炁
    0.47
    ଃ
    0.47
    ﺲ
    0.47
    ᱔
    0.46
     आशा
    0.45
    ตุ
    0.45
     vastu
    0.45
    ყო
    0.44
     स्टेज
    0.44
    दा
    0.44
    POSITIVE LOGITS
     इलाकों
    0.48
    i
    0.46
    Locations
    0.45
    iOS
    0.42
     locations
    0.40
     solns
    0.40
    inor
    0.40
    olds
    0.40
    Default
    0.39
    Where
    0.39
    Act Density 0.001%

    No Known Activations