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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     made
    -3.08
    made
    -2.58
    Made
    -2.22
     Made
    -2.16
     MADE
    -1.95
    MADE
    -1.63
     dibuat
    -1.49
     hecha
    -1.44
     gemaakt
    -1.43
     feitos
    -1.41
    POSITIVE LOGITS
     ſeveral
    0.85
     Monfieur
    0.84
    ]='\
    0.77
    JsonHelper
    0.75
     Paglinawan
    0.75
     uſe
    0.74
     Theſe
    0.74
     "..\..\
    0.71
     sure
    0.69
    +:+
    0.68
    Act Density 0.043%

    No Known Activations