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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     иногда
    -0.07
     scenic
    -0.07
    ,strlen
    -0.07
     Ket
    -0.07
     leasing
    -0.06
     dě
    -0.06
    Bru
    -0.06
     Server
    -0.06
     önce
    -0.06
     cores
    -0.06
    POSITIVE LOGITS
     sdl
    0.07
     Licensed
    0.06
    mach
    0.06
    oward
    0.06
    َق
    0.06
    EXTERNAL
    0.06
    Grace
    0.06
    rung
    0.06
     бух
    0.06
    juana
    0.06
    Act Density 0.006%

    No Known Activations