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

    Neuronpedia

    INDEX
    Explanations

    responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Immediately
    -0.07
     lurking
    -0.07
    ome
    -0.06
    ाध
    -0.06
    ainty
    -0.06
     온
    -0.06
    Akt
    -0.06
    ereo
    -0.06
     Morph
    -0.06
    ē
    -0.06
    POSITIVE LOGITS
    [cell
    0.08
    ,DB
    0.07
    <TreeNode
    0.06
    ’ex
    0.06
     responses
    0.06
    ))
↵
    0.06
    ]]
↵
    0.06
    	files
    0.06
    अब
    0.06
     CHAR
    0.06
    Act Density 0.014%

    No Known Activations