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

    Neuronpedia

    INDEX
    Explanations

    price

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	tmp
    -0.06
     deaths
    -0.06
     females
    -0.06
    words
    -0.06
     bodies
    -0.06
    	State
    -0.06
    	product
    -0.06
     publish
    -0.06
     State
    -0.06
    years
    -0.06
    POSITIVE LOGITS
    าหล
    0.07
     потол
    0.07
    suspend
    0.07
    :+
    0.07
     |_|
    0.07
    ）↵
    0.06
     빛
    0.06
     hade
    0.06
     ={↵
    0.06
    通常
    0.06
    Act Density 0.029%

    No Known Activations