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

    Neuronpedia

    INDEX
    Explanations

    code, technical jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /constants
    -0.06
    /assets
    -0.06
    	hs
    -0.06
     samo
    -0.06
    atar
    -0.06
    社
    -0.06
     FR
    -0.06
     Sunday
    -0.06
    목
    -0.06
     ฮ
    -0.06
    POSITIVE LOGITS
     Nicholas
    0.07
    ellery
    0.07
     fil
    0.06
    Measured
    0.06
     утвержд
    0.06
    (seconds
    0.06
     cabins
    0.06
    ，其
    0.06
    ạn
    0.06
     %>
    0.06
    Act Density 0.000%

    No Known Activations