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

    Neuronpedia

    INDEX
    Explanations

    purposes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Enllaces
    -0.83
     betweenstory
    -0.79
    Vidite
    -0.78
     Jefus
    -0.78
    RegressionTest
    -0.73
     mergeFrom
    -0.71
     Monfieur
    -0.70
     fubject
    -0.69
     themſelves
    -0.68
    はじめに
    -0.68
    POSITIVE LOGITS
     and
    0.90
    ,
    0.85
     or
    0.74
    .
    0.68
     &
    0.67
     plus
    0.59
     +
    0.59
    /
    0.58
     a
    0.57
     especially
    0.57
    Act Density 0.056%

    No Known Activations