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

    Neuronpedia

    INDEX
    Explanations

    providing information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indicates
    -0.86
     indicate
    -0.85
     thereunder
    -0.81
     indicating
    -0.79
     Indicates
    -0.72
    indicate
    -0.72
     Cister
    -0.71
     indication
    -0.70
     underneath
    -0.69
    s
    -0.69
    POSITIVE LOGITS
     single
    0.73
     local
    0.69
     sole
    0.68
    ratulations
    0.66
    ugeot
    0.66
     first
    0.64
    matchCondition
    0.63
    ipal
    0.62
     createState
    0.60
     non
    0.60
    Act Density 0.561%

    No Known Activations