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

    Neuronpedia

    INDEX
    Explanations

    say "network"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Agency
    -0.07
    output
    -0.07
     сохран
    -0.07
    Special
    -0.07
    IData
    -0.06
     phản
    -0.06
    Helper
    -0.06
     webcam
    -0.06
    洞
    -0.06
     एड
    -0.06
    POSITIVE LOGITS
     goggles
    0.06
     신입
    0.06
    sand
    0.06
     amacı
    0.06
    tru
    0.06
     redistrib
    0.05
    _js
    0.05
    kees
    0.05
     whims
    0.05
    сы
    0.05
    Act Density 0.058%

    No Known Activations