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

    Neuronpedia

    INDEX
    Explanations

    business names and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    with
    0.46
    at
    0.40
    ीकरण
    0.39
    Int
    0.38
    All
    0.38
    IE
    0.37
    on
    0.35
    of
    0.35
    IS
    0.35
    v
    0.35
    POSITIVE LOGITS
     isang
    0.46
     Ltd
    0.43
     LTD
    0.43
     Masaki
    0.42
     anos
    0.42
     morate
    0.42
     સેવા
    0.42
     marcó
    0.41
     nahi
    0.40
     mutta
    0.40
    Act Density 0.147%

    No Known Activations