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

    Neuronpedia

    INDEX
    Explanations

    Removing impurities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _returns
    -0.07
    IFF
    -0.06
    確認
    -0.06
    .Label
    -0.06
    提
    -0.06
    ?type
    -0.06
    recall
    -0.06
    RIA
    -0.06
    -actions
    -0.06
     흔
    -0.06
    POSITIVE LOGITS
    admin
    0.07
     strom
    0.06
     incredible
    0.06
    _tran
    0.06
     flawed
    0.06
    dont
    0.06
     ft
    0.06
     sorrow
    0.06
     communist
    0.06
     incredibly
    0.06
    Act Density 0.016%

    No Known Activations