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

    Neuronpedia

    INDEX
    Explanations

    numbers question Reset Game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kow
    0.42
     saut
    0.38
    плу
    0.38
    Με
    0.38
    諏
    0.38
     Cochran
    0.38
    proc
    0.37
     Euras
    0.37
    ួល
    0.37
    any
    0.36
    POSITIVE LOGITS
    ㅅ
    0.43
    ifaiFace
    0.41
    ifika
    0.41
     Roundup
    0.41
     शानदार
    0.40
    ိုင်း
    0.40
     Performing
    0.39
    storeItem
    0.39
    ESSITY
    0.39
    tiden
    0.39
    Act Density 0.011%

    No Known Activations