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

    Neuronpedia

    INDEX
    Explanations

    specific practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MAPE
    0.50
    ০০
    0.47
     مکان
    0.45
     Tibetan
    0.45
     передачи
    0.44
    ampton
    0.44
     ব্যাপক
    0.44
     بر
    0.43
    vät
    0.42
     دیکھیں
    0.42
    POSITIVE LOGITS
     која
    0.49
     عندنا
    0.48
     welke
    0.47
    िलो
    0.45
    affeine
    0.44
    愚
    0.43
    ឹក
    0.43
     vem
    0.43
     disposiciones
    0.42
    棲
    0.41
    Act Density 0.000%

    No Known Activations