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

    Neuronpedia

    INDEX
    Explanations

    Grid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Process
    -0.07
     pork
    -0.07
    اهش
    -0.06
    yu
    -0.06
    -com
    -0.06
     Darwin
    -0.06
    رفت
    -0.06
    "B
    -0.06
     plainly
    -0.06
    +":
    -0.06
    POSITIVE LOGITS
    ieties
    0.07
    í
    0.06
     &)
    0.06
     asyncio
    0.06
     rowData
    0.06
     Proposed
    0.06
     Treasurer
    0.06
     ED
    0.06
    ább
    0.06
     ()=>
    0.06
    Act Density 0.003%

    No Known Activations