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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Pru
    -0.66
    awar
    -0.63
     Westminster
    -0.62
     Faust
    -0.62
    andem
    -0.61
    ueller
    -0.59
    eki
    -0.59
     Midlands
    -0.59
     Bris
    -0.59
     Fukushima
    -0.58
    POSITIVE LOGITS
    DOS
    0.71
    FLAG
    0.68
    ovic
    0.66
    Äĩ
    0.65
    BILL
    0.64
    Games
    0.63
     SetTextColor
    0.62
    natureconservancy
    0.62
    BOOK
    0.61
    Cro
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.