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

    Neuronpedia

    INDEX
    Explanations

    words related to studies, data, and administration

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     «
    -0.52
    bringung
    -0.51
     
    -0.49
     administration
    -0.47
     A
    -0.46
     i
    -0.45
      
    -0.45
    事件
    -0.43
     An
    -0.43
     Te
    -0.42
    POSITIVE LOGITS
     Theſe
    1.05
    RegistryLite
    1.02
     auffi
    1.00
     theſe
    0.96
     fubject
    0.93
     becauſe
    0.92
     leaſt
    0.92
     Jefus
    0.91
    Geplaatst
    0.91
    }))
    0.91
    Act Density 3.194%

    No Known Activations