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

    Neuronpedia

    INDEX
    Explanations

    mate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mate
    -2.75
    mate
    -2.28
     mates
    -2.03
    Mate
    -1.95
     Mate
    -1.88
    mates
    -1.78
     MATE
    -1.76
    MATE
    -1.69
     buddy
    -1.26
     friend
    -1.05
    POSITIVE LOGITS
    σκ
    0.51
    롯
    0.50
    ilov
    0.49
    icana
    0.48
    ignty
    0.48
    瞰
    0.48
     Awards
    0.47
    TTI
    0.46
    utory
    0.46
    ysan
    0.46
    Act Density 0.073%

    No Known Activations