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

    Neuronpedia

    INDEX
    Explanations

    Scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pees
    -0.07
    ₎
    -0.07
     ')↵
    -0.06
     thickness
    -0.06
    pickle
    -0.06
    Mapping
    -0.06
    License
    -0.06
     sticks
    -0.06
    ningar
    -0.06
     mMap
    -0.06
    POSITIVE LOGITS
    Reports
    0.08
    goals
    0.07
    uploader
    0.06
    _areas
    0.06
     Бр
    0.06
    为民
    0.06
    Selection
    0.06
    	part
    0.06
    /common
    0.06
    _goals
    0.06
    Act Density 0.011%

    No Known Activations