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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    依托
    -0.07
    发展空间
    -0.07
     CONFIG
    -0.07
    	flash
    -0.07
    caffold
    -0.06
    ulti
    -0.06
    公然
    -0.06
     struggle
    -0.06
    	bt
    -0.06
     timestep
    -0.06
    POSITIVE LOGITS
    Berlin
    0.08
    تقنية
    0.07
    isher
    0.07
    쑈
    0.07
     цена
    0.07
    lname
    0.07
    嵯
    0.07
    Naz
    0.07
     letz
    0.07
    cean
    0.07
    Act Density 0.892%

    No Known Activations