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

    Neuronpedia

    INDEX
    Explanations

    three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rails
    -0.07
    星
    -0.06
    قال
    -0.06
    sidebar
    -0.06
    ья
    -0.06
    における
    -0.06
     soutěže
    -0.06
    тери
    -0.06
    $user
    -0.06
    .The
    -0.06
    POSITIVE LOGITS
     desirable
    0.07
    	process
    0.06
    distributed
    0.06
     Penalty
    0.06
    Highest
    0.06
     obsess
    0.06
     Details
    0.06
     çek
    0.06
     LOGGER
    0.06
    Transfer
    0.06
    Act Density 0.000%

    No Known Activations