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

    Neuronpedia

    INDEX
    Explanations

    condemned to be free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    óg
    0.47
    पं
    0.45
    prend
    0.44
     gamblers
    0.43
     politicians
    0.43
     bloggers
    0.42
    rama
    0.42
    City
    0.40
     collective
    0.39
     ब्ले
    0.39
    POSITIVE LOGITS
     DIN
    0.53
     Höhen
    0.52
    UWORD
    0.48
     PYTHONPATH
    0.48
     আকারের
    0.48
     NAO
    0.48
     Yunan
    0.47
     Taro
    0.47
     تاک
    0.47
     Comparator
    0.47
    Act Density 0.002%

    No Known Activations