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

    Neuronpedia

    INDEX
    Explanations

    API

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oux
    -0.07
     satellite
    -0.07
     Aquarium
    -0.07
     snow
    -0.07
     guarantees
    -0.07
    漂
    -0.06
     Dog
    -0.06
     Prep
    -0.06
     Springs
    -0.06
    UMAN
    -0.06
    POSITIVE LOGITS
     WINAPI
    0.08
     επισ
    0.06
    문화
    0.06
     controvers
    0.06
    เลย
    0.06
     Thinking
    0.06
     Especially
    0.06
     espan
    0.06
     bude
    0.06
    HAVE
    0.06
    Act Density 0.013%

    No Known Activations