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

    Neuronpedia

    INDEX
    Explanations

    processes and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ле
    0.56
    甯
    0.50
     meninos
    0.48
    л
    0.48
    兒童
    0.48
     condizione
    0.47
    leyici
    0.47
    я
    0.46
     ಸಮಸ್ಯ
    0.46
     ನಿಮಗೆ
    0.46
    POSITIVE LOGITS
     WWE
    0.45
     Über
    0.43
     boat
    0.43
     MOSFET
    0.43
     snowboard
    0.42
     FU
    0.40
     IEEE
    0.40
     berat
    0.39
     vapor
    0.39
     Vapor
    0.38
    Act Density 0.004%

    No Known Activations