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

    Neuronpedia

    INDEX
    Explanations

    .org/ or .com/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    बूझ
    0.34
     Substituting
    0.30
    一篇
    0.29
     Automat
    0.29
     Sabemos
    0.29
     Нужно
    0.28
     Anzahl
    0.28
    ებთ
    0.28
    嵃
    0.27
     Considerable
    0.27
    POSITIVE LOGITS
    /
    0.41
     sites
    0.37
    //
    0.35
    /,
    0.34
     web
    0.33
     website
    0.32
    /"
    0.32
    /?
    0.32
     products
    0.32
     membership
    0.32
    Act Density 0.102%

    No Known Activations