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

    Neuronpedia

    INDEX
    Explanations

    relativity and space-time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Be
    -0.07
    _rep
    -0.07
     unint
    -0.07
    asm
    -0.07
    /app
    -0.07
    View
    -0.06
    造
    -0.06
     Gulf
    -0.06
     Ethi
    -0.06
    value
    -0.06
    POSITIVE LOGITS
    边界
    0.08
    rimon
    0.07
    Gender
    0.07
     recruiters
    0.07
    上司
    0.07
     hallway
    0.07
    收录
    0.07
    县政府
    0.07
    授予
    0.07
     werd
    0.07
    Act Density 0.013%

    No Known Activations