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

    Neuronpedia

    INDEX
    Explanations

    time and weather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Byte
    -0.08
    according
    -0.07
     specify
    -0.07
    Convention
    -0.07
     specifics
    -0.07
    決
    -0.07
    “But
    -0.07
    alog
    -0.06
     senate
    -0.06
     Handle
    -0.06
    POSITIVE LOGITS
    再来
    0.08
     destabil
    0.07
    重返
    0.07
    外墙
    0.07
    opus
    0.07
    תשע
    0.06
    .MapFrom
    0.06
    ="{{$
    0.06
     أعمال
    0.06
    .!
    0.06
    Act Density 0.095%

    No Known Activations