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

    Neuronpedia

    INDEX
    Explanations

    designs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Å
    -0.07
     вк
    -0.07
     nag
    -0.06
     bigot
    -0.06
     SMS
    -0.06
     Brigham
    -0.06
     TESTING
    -0.06
     channel
    -0.06
    福利
    -0.06
    础
    -0.06
    POSITIVE LOGITS
     sia
    0.07
     Dominic
    0.07
    ч
    0.06
    _os
    0.06
    Modern
    0.06
    izophren
    0.06
     Prepared
    0.06
    _preferences
    0.06
    그래
    0.06
     tud
    0.06
    Act Density 0.065%

    No Known Activations