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

    Neuronpedia

    INDEX
    Explanations

    Mar followed by a word part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (',
    0.42
    prev
    0.36
     trece
    0.35
    ாய்ச்ச
    0.35
    ütün
    0.34
    Confident
    0.34
    мя
    0.34
    firebase
    0.34
    dés
    0.33
    aluronic
    0.33
    POSITIVE LOGITS
     specialising
    0.37
     palju
    0.37
    关系的
    0.37
    েন
    0.36
    ምት
    0.36
    तरीय
    0.36
    宽高
    0.36
    ན
    0.36
     \<
    0.35
     любого
    0.35
    Act Density 0.003%

    No Known Activations