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

    Neuronpedia

    INDEX
    Explanations

    Code and typos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    know
    -0.07
    icides
    -0.06
    Архів
    -0.06
     �
    -0.06
    .any
    -0.06
     saturated
    -0.06
    	html
    -0.06
    	use
    -0.06
    	Editor
    -0.06
    โครงการ
    -0.06
    POSITIVE LOGITS
    pan
    0.07
    -G
    0.07
    nání
    0.07
    eç
    0.06
    ;break
    0.06
    smith
    0.06
    acak
    0.06
    CHAPTER
    0.06
     Düz
    0.06
    cef
    0.06
    Act Density 0.059%

    No Known Activations