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

    Neuronpedia

    INDEX
    Explanations

    Dimensions and Amounts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.72
     purpoſe
    -0.50
    criminator
    -0.49
     figliu
    -0.48
     Democrá
    -0.48
     Independiente
    -0.47
     autoradio
    -0.46
     Shakspeare
    -0.46
     Económica
    -0.45
     Châu
    -0.43
    POSITIVE LOGITS
     Hours
    0.88
     Min
    0.87
     Seeds
    0.85
     Levels
    0.84
     Pieces
    0.82
     Miles
    0.80
     Parts
    0.79
     Moves
    0.78
     Spaces
    0.77
     Sessions
    0.76
    Act Density 0.001%

    No Known Activations