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

    Neuronpedia

    INDEX
    Explanations

    lists ending in etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    2.53
    ло
    2.22
    Dü
    1.81
    ০
    1.77
    tte
    1.74
    ну
    1.71
    𝙉
    1.71
    ﺯ
    1.70
    𝙍
    1.70
    ларга
    1.70
    POSITIVE LOGITS
    etera
    2.00
    ities
    1.53
    등
    1.53
    于是
    1.35
     bacter
    1.34
     annoncé
    1.30
     réalisée
    1.30
    k
    1.29
    ோர்
    1.26
     suburbs
    1.26
    Act Density 0.124%

    No Known Activations