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

    Neuronpedia

    INDEX
    Explanations

    frequently visited places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     किंवा
    0.51
    ningarna
    0.50
     কিংবা
    0.50
    或者
    0.48
    劻
    0.46
    ide
    0.45
    šek
    0.43
     уеннары
    0.42
    eder
    0.41
    或其他
    0.41
    POSITIVE LOGITS
     lured
    0.55
     ionic
    0.46
     suits
    0.45
     tangled
    0.45
     sinusoidal
    0.45
     Vantage
    0.45
     Sinatra
    0.44
     H
    0.44
     vinegar
    0.44
     Honeywell
    0.44
    Act Density 0.001%

    No Known Activations