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

    Neuronpedia

    INDEX
    Explanations

    start of code or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vee
    1.33
     nombreux
    1.30
     DATE
    1.25
    糗
    1.25
     (£
    1.18
    icksburg
    1.14
     событий
    1.14
    が進
    1.14
     hee
    1.13
     Ramb
    1.12
    POSITIVE LOGITS
    rinsic
    2.52
    6
    2.44
    7
    2.36
     чтобы
    2.30
     lugar
    2.28
    othing
    2.28
    8
    2.27
    0
    2.24
    genuine
    2.20
    Azur
    2.19
    Act Density 0.317%

    No Known Activations