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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Science
    -0.08
    715
    -0.06
     apartments
    -0.06
    missions
    -0.06
    spa
    -0.06
    PLL
    -0.06
    guna
    -0.06
    YYYY
    -0.06
    pair
    -0.06
    viewModel
    -0.06
    POSITIVE LOGITS
    <len
    0.06
     obsessed
    0.06
    (EIF
    0.06
    ccion
    0.06
     kız
    0.06
    َل
    0.06
     �
    0.06
    微笑
    0.06
     квітня
    0.06
     fís
    0.06
    Act Density 0.008%

    No Known Activations