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

    Neuronpedia

    INDEX
    Explanations

    code configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _levels
    -0.07
    batis
    -0.06
    	dt
    -0.06
     Lower
    -0.06
     Record
    -0.06
    /catalog
    -0.06
     merges
    -0.06
    (textBox
    -0.06
    (depth
    -0.06
    (ar
    -0.06
    POSITIVE LOGITS
     призна
    0.07
     Darth
    0.06
     отвер
    0.06
    getSingleton
    0.06
     bounding
    0.06
    finally
    0.06
     Maryland
    0.06
    alers
    0.06
    AJ
    0.06
    анию
    0.06
    Act Density 0.071%

    No Known Activations