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

    Neuronpedia

    INDEX
    Explanations

    from './' imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bracketing
    0.48
    ObjectTemp
    0.43
    Mientras
    0.40
    𒄩
    0.40
    Dios
    0.40
     появилась
    0.39
     rappro
    0.39
    ক্কা
    0.39
    ल्लभ
    0.39
    اونلو
    0.39
    POSITIVE LOGITS
     './
    1.22
     "./
    1.20
     ./
    1.00
    "./
    0.99
     '../
    0.91
     `./
    0.90
    ('./
    0.86
     "../
    0.83
    ./
    0.83
    ("./
    0.82
    Act Density 0.002%

    No Known Activations