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

    Neuronpedia

    INDEX
    Explanations

    od

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Agencies
    -0.07
     taxed
    -0.07
    妻
    -0.07
    Utility
    -0.07
    connection
    -0.07
     Status
    -0.07
    .Router
    -0.07
    iasm
    -0.07
     entreprises
    -0.07
    tweet
    -0.06
    POSITIVE LOGITS
     OD
    0.07
    ?s
    0.06
     midfield
    0.06
    -rule
    0.06
    acağ
    0.06
    _dis
    0.06
    ��
    0.06
     ordinarily
    0.06
     Ses
    0.06
    braska
    0.06
    Act Density 0.001%

    No Known Activations