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

    Neuronpedia

    INDEX
    Explanations

    automotive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     иг
    -0.08
    ority
    -0.07
     cumpleaños
    -0.07
     comunit
    -0.07
     awkward
    -0.07
     Terry
    -0.07
    恩
    -0.07
    帳
    -0.07
    portunity
    -0.07
    crud
    -0.07
    POSITIVE LOGITS
     내부
    0.09
     компонентов
    0.09
    联网
    0.08
    内部
    0.08
     interiors
    0.08
     visor
    0.08
    industrie
    0.08
    ಮುಖ
    0.08
    厂
    0.08
     modernization
    0.08
    Act Density 0.020%

    No Known Activations