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

    Neuronpedia

    INDEX
    Explanations

    code syntax and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    溇
    0.50
    陖
    0.49
    飧
    0.48
    ProductsStore
    0.45
     организма
    0.45
     ليست
    0.45
     coagulation
    0.44
     săptăm
    0.44
     Wastewater
    0.44
    Ỳ
    0.44
    POSITIVE LOGITS
    s
    0.53
     don
    0.46
     If
    0.46
    plex
    0.46
    n
    0.46
    r
    0.46
    t
    0.45
     simplify
    0.44
     simplifies
    0.44
     doesn
    0.43
    Act Density 0.001%

    No Known Activations