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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     samt
    -0.07
    :D
    -0.07
     burden
    -0.06
     enclosure
    -0.06
     detections
    -0.06
     Cabinets
    -0.06
     Stations
    -0.06
     listeners
    -0.06
    nth
    -0.06
     imap
    -0.06
    POSITIVE LOGITS
    etically
    0.07
    造
    0.07
    ajax
    0.07
    objectId
    0.07
     //////////
    0.06
    ibili
    0.06
     Schema
    0.06
     Husband
    0.06
     Fetish
    0.06
     아무
    0.06
    Act Density 0.001%

    No Known Activations