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

    Neuronpedia

    INDEX
    Explanations

    sumerge, sumerge, Dataset, application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enterprise
    0.42
     chaff
    0.40
    enterprise
    0.40
     constant
    0.39
     having
    0.37
     généraux
    0.37
    મે
    0.36
     constante
    0.36
     costante
    0.36
     konci
    0.36
    POSITIVE LOGITS
     სპ
    0.42
    Dataset
    0.40
    IOD
    0.40
    铖
    0.40
    TabData
    0.39
     Dataset
    0.39
    Breakfast
    0.39
    Task
    0.38
    夏の
    0.38
    Kumar
    0.38
    Act Density 0.002%

    No Known Activations