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
     love
    -1.03
    mate
    -0.84
     mates
    -0.80
     mate
    -0.79
    mates
    -0.79
     sports
    -0.78
     DC
    -0.70
     Sports
    -0.68
    love
    -0.67
     LOVE
    -0.65
    POSITIVE LOGITS
     صوتيه
    0.86
    \{\\
    0.71
     Sandstone
    0.71
    manship
    0.64
     يتيمه
    0.64
    Santis
    0.64
    ValueStyle
    0.63
    WaitGroup
    0.63
     Dominus
    0.63
     Biôgrafia
    0.63
    Act Density 0.275%

    No Known Activations