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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARG
    -0.06
    _NORMAL
    -0.06
     бы
    -0.06
     我
    -0.06
     DOS
    -0.06
    Manifest
    -0.06
     carniv
    -0.06
    。あ
    -0.06
    orsch
    -0.06
    struct
    -0.06
    POSITIVE LOGITS
     통합
    0.07
     Wu
    0.06
     ref
    0.06
     wasm
    0.06
     medidas
    0.06
    Painter
    0.06
    Span
    0.06
     Конститу
    0.06
     обла
    0.06
     â
    0.06
    Act Density 0.000%

    No Known Activations