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

    Neuronpedia

    INDEX
    Explanations

    lex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้านด
    -0.06
     Anton
    -0.06
     entrada
    -0.06
     coats
    -0.06
     Orn
    -0.06
    岩
    -0.06
     Byron
    -0.06
     Nina
    -0.06
    	stats
    -0.06
    迎
    -0.06
    POSITIVE LOGITS
    MUX
    0.08
     mux
    0.07
     linker
    0.07
     Luxembourg
    0.07
    hr
    0.07
     GH
    0.06
    mutex
    0.06
     safeguards
    0.06
    mux
    0.06
     Places
    0.06
    Act Density 0.002%

    No Known Activations