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

    Neuronpedia

    INDEX
    Explanations

    certain aspects of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     थीम
    0.55
    anians
    0.49
    InsertInt
    0.48
    ण
    0.48
    SaveFolder
    0.47
    allenges
    0.47
    ㇁
    0.47
     ಥ
    0.47
     inhomogeneities
    0.46
    ㄶ
    0.46
    POSITIVE LOGITS
    owe
    0.47
    กว่า
    0.47
    рий
    0.45
     cercano
    0.44
     d
    0.44
    ждая
    0.43
    тали
    0.42
     exposição
    0.42
     pergunta
    0.41
    сел
    0.41
    Act Density 0.001%

    No Known Activations