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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enzymes
    -0.07
    -string
    -0.07
    LICENSE
    -0.07
    ické
    -0.07
     Barbara
    -0.07
    벽
    -0.07
     району
    -0.06
    机场
    -0.06
    segue
    -0.06
    .classes
    -0.06
    POSITIVE LOGITS
    content
    0.09
    .content
    0.08
     bitter
    0.08
    ensation
    0.07
    (ident
    0.07
     Kv
    0.06
     الات
    0.06
    	content
    0.06
    _ED
    0.06
     المل
    0.06
    Act Density 0.002%

    No Known Activations