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

    Neuronpedia

    INDEX
    Explanations

    Do you want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     merits
    0.58
     nuanced
    0.58
     couldn
    0.55
     mismanagement
    0.53
     subtle
    0.53
     shouldn
    0.51
     diminishes
    0.51
     destabil
    0.51
     inexplicable
    0.51
     achievable
    0.50
    POSITIVE LOGITS
     tiga
    0.66
     diğer
    0.59
     directorio
    0.59
     különböző
    0.58
     இரண்டு
    0.58
     。,
    0.57
     üç
    0.57
    Tổng
    0.56
    ſ
    0.56
     Nachricht
    0.56
    Act Density 0.166%

    No Known Activations