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

    Neuronpedia

    INDEX
    Explanations

    instruction examples or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificar
    0.36
    inen
    0.34
     woven
    0.34
    ens
    0.34
    ier
    0.33
     पर्दे
    0.33
     tapped
    0.33
     tap
    0.32
    tten
    0.32
     آئینے
    0.31
    POSITIVE LOGITS
    Arkadaşlar
    0.37
    QUOTE
    0.36
     (...)
    0.36
    回复
    0.35
    […]
    0.35
    (...)
    0.35
    Minecraft
    0.35
     "...
    0.34
     দিলে
    0.33
    Zitat
    0.33
    Act Density 0.001%

    No Known Activations