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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    建筑工程
    -0.08
    _Api
    -0.07
    的文字
    -0.07
     отдых
    -0.07
    pository
    -0.07
     synthesis
    -0.07
     preprocess
    -0.07
     administration
    -0.07
    𬜬
    -0.07
    restart
    -0.07
    POSITIVE LOGITS
     tatsäch
    0.07
     kle
    0.06
     slated
    0.06
    传销
    0.06
     какие
    0.06
    ńska
    0.06
     Feld
    0.06
    _MEDIUM
    0.06
     WITH
    0.06
    encers
    0.06
    Act Density 0.026%

    No Known Activations