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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    capt
    -0.07
    agn
    -0.07
    ♪↵↵
    -0.07
     advisers
    -0.07
    _ui
    -0.07
    degree
    -0.07
    inz
    -0.06
    Aware
    -0.06
    	ps
    -0.06
     annotation
    -0.06
    POSITIVE LOGITS
    .GroupLayout
    0.08
     Changed
    0.06
     voices
    0.06
    LIGHT
    0.06
     наз
    0.06
    มหาว
    0.06
     입
    0.06
     Lagos
    0.06
     verk
    0.06
     slov
    0.06
    Act Density 0.058%

    No Known Activations