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

    Neuronpedia

    INDEX
    Explanations

    backend service repository

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neutrons
    0.42
    örungen
    0.41
     திரும்பி
    0.38
    ಿತಿ
    0.38
    <unused58>
    0.37
     galvanized
    0.37
    InitStruct
    0.37
    興趣
    0.37
     latérales
    0.36
    DependentUpon
    0.36
    POSITIVE LOGITS
     서비스를
    0.41
     database
    0.40
    ODB
    0.39
     CRUD
    0.38
     api
    0.37
     സേ
    0.36
     db
    0.35
    CRUD
    0.35
     knowledgeable
    0.34
     roj
    0.34
    Act Density 0.008%

    No Known Activations